'N 8@p ! /hYWOMOM OMOMOMOMOMQOMQOMOMOMOMhOMPMPMDPMpDPMIPMxIPM#MPM#MPMVPMpVPMYPM<YPMmPMmPM[PMD [PMPML PMPM PMPMD PMPM PMPM PM PMx PMPMPMPMPM,QM,QMO/QMO/QM39QM 39QMmQM mQM{QMJ{QMUQMUQMQMJQMQMzQMRMRM[RMJ[RMSMjSMSMBSMTMrTMTUM TUM1gUM2"} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pi b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pi b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pi  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes1152patternContiguousinvocations1 bJoperation.3exchange\"R$`b@}0 4 i   @tD<p @tD x!"#$%"&&H'Bk(ҍ)b*+,-:.2]/0R12B3)4bL5n67892:;b><a=>2?@bA+BjgC DrEFr[GʗHrI JCK~L²MNONPQRSTSUVWX"#Y"WZ2[2\B]B'^R[_R`baRb c+ dbN ep f g h i:j*]klJmnjo p,qOrqs:tʶuZvwzx Aycz:{ʨ|j} ~:3UjbM=2y2Pʄʸ Tʈʼ$Xʌ( \ ʐ   , O Jr : ʷ Z  z  B d *  J  j 3 V y  :  Z % zH  k  *  J z:]JB;w+zgFzJ~N4hʜ8lʠJ:=_Zz  */QJtږj!C:fʈZz 5*XzJz'JgB[J D x    H |    L     P     T     ! "z6 #jY ${ % & ' (:)(*ZK+m,z- ./*01J=2_3j4567 8:/9Q:Zt;<z=>?J!@CAzBҿCrD;E"xFzGH*-I*aJ*K*L*M*1N*eO*P*Q*R*5S*iT*U*V*W*9X*mY*Z*[* \*=]*q^*_*`* a0bRcud*efJghj"iDjgklm:noZp6qzYr |st*uvJw(xjKymz{|}J~z= `WR ZIZ}ZZZZMZZZZ ZQ Z Z Z Z!!ZU!Z!Z!Z!Z%"ZY"Z"Z"Z"Z)#JL#n#ʑ#Z##z# $>$*a$$J$$j$ %0%S%u%:%ʺ%Z%%z"& E&g&*&&J&& B3 U bx  Z 3 Rp   Z% a    1 e    5 i    : n ʢ    > r ʦ   B e J :  Z  z5  X z *  J  j' I l   :  Z ; z^   *  J - jP r  *  "Q z  * B ~ ڲ   N ڂ ڶ   R چ ں  " V ڊ ھ  & Z ڎ   * ^ !ʁ "Z #J $ %j  &. 'Q (t ) *: + ,Z -  .zC / f 0 1* 2 3J 4 5j5 6W 7z 8 9 :: ; <Z' =I >l ? @ AZ B- CRm D E FZ" G^ H  I  J  K 7 L k M  N  O  P ; Q o R  S  T  U ? V s W  X  Y  Z C [ w \  ]  ^  _ G ` { a b cz d  e( f*K gm hJ iڲ jj k l m= n_ o: pʤ qZ r sz t / uQ v*t w xJ y zj { ! |C! }f! ~! J! !  " I" " " 2# ># z# :# :# :$ :S$ :$ :$ :$ :#% :W% :% :% :% :'& :[& :& :& :& :+' :_' :' :' :' :/( :c( :( *( ( ( :") D) Zg) ) z)  ) ) ** 6* JY* {* j* * * + (+ :K+ m+ Z+ + z+  + , *=, _, J, , z, , )- f- -  - b. Z. . j. j/ j;/ jo/ j/ j/ j 0 j?0 js0 j0 j0 j1 jC1 jw1 j1 j1 j2 jG2 j{2 j2 j2 j3 jK3 j3 j3 Z3 3 4 j>4 `4 4 4 4 :4  5 Z05 R5 zu5  5 5 *5 5 J"6 D6 jg6 6 6 6 6 :7 67 ZY7 {7 z7 7 7 J8 E8 B8 8 :8 :9 v9 B9 9 #: W: : : : '; [; ; ; ; +< _< < < < /= c= = = = 3> g> > > !> "? # 8? $Z? %*}? &? 'J? (? )j@ *)@ +L@ ,o@ -@ .:@ /@ 0Z@ 1A 2z>A 3 aA 4A 5*A 6A 7JA 8 B 9j0B :RB ;uB <B =B >JB ?B @z"C AbC BrC CC DRD EYD FD GZD HE IBE JvE KE LE MF NFF OzF PF QF RG SJG T~G UG VG WH XNH YH ZH [H \I ]RI ^I _I `I aJ b24J c"WJ dyJ eBJ fҾJ gbJ hK i&K jIK kkK l2K m°K nRK oK prL q;L r]L s"L tL uBL vL wb M x,M yOM zrM {M |2M }M ~bM  :: y 2  *2 n ڪ 2 # W    ' [    + _    / c    3 g    z&  I k    :  Z; ] z    *  J- O jr     : A Zd  z   J 3 V *  " zN Ҋ *  ? s ڧ   C w ګ   G { گ   K  ڳ   O ڃ ڷ   B Ze J ڪ j   5 W :z ʜ Z  z  ' I *l  J  j  ; ^  :  Z   - :P r z  r. j " z  *\ * * * *, *` * * * *0 *d * * * *4 *h * * * *8 *l * * * *< !_ " # $* % &J  '. (jQ )s * + , -: .  /ZC 0e 1z 2  3 4* 5 6J5 7W 8jz 9 : ; <! =J'! >I! ?zl! @ ! A! B " CJ" D" ER" F" G<# HZx# IZ# JZ# KZ$ LZH$ MZ|$ NZ$ OZ$ PZ% QZL% RZ% SZ% TZ% UZ& VZP& WZ& XZ& YZ& ZZ ' [ZT' \Z' ]Z' ^Z' _Z$( `ZX( aJ{( bڝ( c( dZ( e) fz() g K) hm) i*) j) kJ) l) mj* n<* o_* p* q* r:* s* tZ + u.+ vzQ+ w t+ x+ y*+ z+ {J+ | , }zC, ~ f, , :, , 2'- f- *- - . 2X. . . . 0/ d/ / / 0 40 h0 0 0 1 81 l1 1 1 2 <2 p2 2 2  3 @3 t3 z3  3 3 3 "4 D4 :g4 ʉ4 Z4 4 z4  5 65 *Y5 {5 J5 5 j5 6 (6 K6 m6 :6 ʲ6 Z6 6 z7  =7 _7 :7 ڤ7 j7  8 bC8 8 Z8 8  89 bt9 9 9 : L: : : : ; P; ; ; ;  < T< < < < $= X= = = = (> \> > > :> *> ? J>? `? j? ? ? ?  @ :0@ R@ Zu@ @ z@  @ @ *"A DA JgA ډA jA A A B 6B :YB {B jB  B B :#C _C 2C C D :TD D D E 4E hE E E F 8F lF F F G L 4`L 5zL 6 L 7L 8*L 9 M :J0M ;RM <juM = M >M ?:M @M Az?N B{N CN DN EB4O FpO GO HZO IjP JjQP KzP LzP MP N!Q OUQ PQ QQ RQ S%R TYR UʍR VR WR X)S Y]S ZS [S \S ] .T ^ bT _T `T a T bU c2U dUU ewU f:U gʼU hZU iV jz$V k GV liV m*V nV oJV pV qjW r8W s[W t~W uW v:W wW xZX y*X zzMX { pX |X }:X ~X jX Y \Y Y Y Z RQZ Z Z J[ Z:[ Zn[ J[ J[ Z \ Z>\ Jr\ J\ Z\ Z] JB] Jv] Z] Z] J^ JF^ Zz^ Z^ J^ J_ ZJ_ Z~_ J_ J_ : ` +` N` Jq` ړ` j` ` ` a @a :ca ʅa Za a za  b 2b *Ub wb Jb ڼb jb c $c Gc ic :c ʮc Zc c zd 7 :z2breasonOperatorInputsvalue7invocations1 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bWuoperation.4ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue8bytes2304patternContiguousinvocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 5u_ b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<5jT >s(]G|& f   bWuoperation.6ipu_stack_copy_u64%:%R)2))2)")B)Z-b1reasonLocalCopyvalue10bytes512patternContiguousinvocations4 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)")B)Z-b1reasonLocalCopyvalue10bytes256patternContiguousinvocations1  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10FF  LL)D*D44>2?2IIST^^hiss}" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 # b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1!$ bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5" bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1FF44 " "  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKllnAoAqqs+t+vvxy{{}}tt^^ӇӉHH22#* b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1$+ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMgEPMgEPM LPM LPMUPM@UPMXPM XPMnPMnPM9PM9PM۵PM ۵PMePM ePMPMd PMPM PMEPM EPMQMP QM-QMp-QMK'?'IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$[%['')E*E,,.///11346689;x;x==?J@JBBD4E4GGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;##mm  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMOMOMOM|OMOMOMQOMQOMOM|OMOMHOMPMPMDPMPDPMIPMXIPM#MPM#MPMVPMPVPMYPMYPMmPMmPMUPM$ UPMPM, PMPM PMPM$ PMPM PMPM| PM{PMX{PMQMQM-QM-QM;QM;QMpQM\pQMQMQMQMQMqRM8qRMIRMIRMSMSMSMSMSTMlSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Of b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Of b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Of  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1G]S  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dGRU<d+r9~CO   Y   c  1 q  =} bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10FF  KK)=*=44>'?'IIS T ^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7operation.6exchange :z2breasonOperatorInputsvalue8invocations1# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z9z="=zA"AzE*EbIreasonOperatorKernelvalue10kernelSpecoutputElements576input0Elements640input1Elements6272invocations1FF22    ##qq] ]""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnpgqgssuMvMxxz3{3}}rrXXˎː>>2Planned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMgEPMgEPM LPM LPMUPM@UPMXPM XPMnPMnPM9PM9PM۵PM ۵PMePM ePMPMd PMPM PMPM PM?QMD ?QM}.QMd}.QMo $   p&f  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL):*:44>$?$IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$I%I'')3*3,,./11346|6|88:f;f==?7@7BBD!E!GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggijlulunnpYqYssu=v=xxz!{!}}ww]]ЉЋCC))  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OM=OM=OMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QMc*>44>(?(IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22""  ""$p%p'')\*\,,.H/H113444668 9 ;;==?h@hBBDPEPGGIPJPLLN8O8QQS T VVXY[|[|]]_d`dbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMqPM qPMPMd PMPM PMQPM QPMQMP QM-QMp-QM 6QML 6QMyQMyQMqQMqQMoQMoQMYRMTYRM1RM1RMkSMkSMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1NnjK b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1  `V. b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1< VY*~KR&zN*"6 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>/?/IIST^^his]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnMoMqqs1t1vvxy{{}}kk݂݄OOqq  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OM=OM=OMOMdOMCOMlCOMOMOMOMOM PM@ PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMyPMyPMPM PMqPM qPMPMd PMPM PMuPM uPMQMH QM-QMh-QM{(r)`|fP8   p X @ = ( :L4 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)6*644>?IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""j j""$R%R''):*:,,."/"113 4 6~6~88:f;f==?3@3BBDEGGIJLLNNPjQjSSUNVNXXZ2[2]]_`bbdegtgtiikXlXnnp>   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMqPM qPMPMd PMPM PM'PM 'PMcQMD cQM.QMd.QM5QM<5QMqyQMqyQMEQMEQMCQMCQMGRMDGRMRMRMYSM YSMSMSM)TMx)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 #C b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 5u b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<5jT >?sx(1Rc bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>!?!IIS T ^^hhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpgqgssuKvKxxz/{/}}PP‰‹44  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMCOMCOMOMdOMOOMlOOMOMOMOMROMPMPMDPMDPM!LPM!LPMUPMUPMXPMzXPMmPMmPMPM PMPM PM}PM }PMPMPMPMPMKPMKPMQMQM-QM -QM6QM6QMyQMyQMQMJ"QM}QM$}QMeRMJ%eRM=RM&=RMwSM )wSMSM*SMTM,TMTUM0TUM7gUM2} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T5u bwBoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*Q*2reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements11521152zinput1Elementsbinvocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T5u bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T5u  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }Aa*J b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1  MX4 b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1< XF08`8h@X  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  TT)F*F44>8?8IIS$T$^^h i sese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbTT F F  88**  "#%y%y'')k*k,,.]/]113O4O668A9A;;=3>3@@B%C%EEGHJJLMO~O~QQSlTlVVXZYZ[[]H^H``b4c4eeghjjlmo{o{qqsatavvxGyG{{}-~-SSŌŎ77  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l OMOMOMOMLOMUOMTUOMOMOMOMOMPM(PM[EPM[EPM'LPM'LPMUPM(UPMXPMXPMnPMnPM-PM-PMPM PMPM PMPML PMPM PM]PM ]PMQM8 QM-QMX-QM)4QM4)4QMQMQM}RM,}RMURMURMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`,  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1XUuz. b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1S bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1J8  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OM=OM=OMOMdOMOOMlOOMOMOMOMOMPM@PMDPMDPM!LPM!LPMUPM@UPMXPM XPMmPMmPMPMPMPM PM}PM }PMPMd PMPM PMcPM cPMQMH QM-QMh-QM6QMD6QMIzQMIzQMQMQMQMQMMRMLMRM%RM%RM_SM_SMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U5u bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U5u bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16j  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U5u  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 5u b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<5jT q>*sc(R W  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbdWeWggi=j=lln!o!qqstvtvtxxzV{V}}88ssUUƎƐ77  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l OMOMOMOMLOM[OMT[OMOMOMOMOMPM(PM[EPM[EPM-LPM-LPMUPM(UPMXPMXPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMKPM KPMQM, QM.QML.QM5QM$5QM'QM'QMeRMeRM=RM=RMwSMwSM;TM;TM TUM TUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ` bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ` bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 `  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~@` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1o&]B } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)=*=44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMIOMIOMOMLOMaOMTaOMOMOM!OM!OMPM(PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM4QM,4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 9y7w  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 9y7w  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 9y7w   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t8Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1?z5  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR)B*B44>2?2IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$j%j'')Z*Z,,.J/J113:4:668*9*;;=>@@B C EEGGIrJrLLN^O^QQSJTJVVX6Y6[[]"^"``bceeggipjplln\o\qqsHtHvvx4y4{{} ~  nnZZБГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMPM PM3QM8 3QMu-QMXu-QM#4QM4#4QMQMQMkRM,kRMCRMCRM}SM}SM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 j. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 j. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U!  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 j.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1F] b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1F bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1;p% } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMCOMCOMOMLOMaOMTaOMOMOM!OM!OMPM(PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 8x6v bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 8x6v bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations17k  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 8x6v  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ;[Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1p+f!/ o  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>&?&IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqvqvssu^v^xxzF{F}}..rrZZ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMUEPMUEPMELPMELPMUPM(UPMYPMYPMnPMnPM'PM'PMPM PMPM PMPML PMPM PM'PM 'PMcQM, cQM.QML.QM5QM$5QM QM QMSRMSRM+RM+RMeSMeSMہTMہTMSUMSUMSfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 k0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 k0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 k0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ws: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1{ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1ZDy#c } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMIOMIOMOMLOMOMTOMOMOMEOMEOMPM(PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PM]PM ]PMQM0 QM-QMP-QM4QM,4QMQMQMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IM@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IM@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IM@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 k&Oo b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1BF0 p  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMgOMTgOMOMOM'OM'OMPM(PMIEPMIEPM9LPM9LPMUPM(UPMXPMXPM}nPM}nPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM8 QM]-QMX]-QM#4QM4#4QMQMQM}RM,}RMURMURMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 j" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 j" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 j"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations14@ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations19n# } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  TT)>*>44>)?)IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''s s""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMIOMIOMOMLOMOMTOMOMOMEOMEOMPM(PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JL> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JL> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JL>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1J N  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMmOMTmOMOMOM-OM-OMPM(PMOEPMOEPM?LPM?LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMQPM QPMQM, QM.QML.QM5QM$5QMQMQMqRMqRMIRMIRMSMSMATMATMTUMRTUMfUMr} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 k$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 k$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 k$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 lht?_ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1y bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X Bw!a } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJoperation.6exchangezOperatorKernel107 :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMUOMTUOMOMOMOMOM!PM(!PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM?QM0 ?QM-QMP-QM#4QM,#4QMύQMύQMRM$RM[RM[RMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 .n5u  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 .n5u  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 .n5u   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Mg  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN3?3IIS!T!^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGI[J[LLNIOIQQS7T7VVX%Y%[[]^``bcexexggifjfllnOoOqqs3t3vvxy{{}}mm߂߄QQÇÉ55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMUOMTUOMOMOMOMOM!PM(!PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM6QM,6QM_QM_QMkRM$kRMCRMCRM}SM}SM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 -m5u  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 -m5u  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 -m5u   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 > b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations14Nm  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMOOMTOOMOMOMOMOMPM(PMCEPMCEPM!LPM!LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PM}PM }PMPML PMPM PM]PM ]PMQM, QM.QML.QM5QM$5QMKQMKQMwRMwRMORMORMSMSMYTMYTM)TUM)TUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 a]^Ff b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1| bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1p,h$\ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  OO)9*944>%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOM[OMT[OMOMOMOMOM'PM('PMDPMDPM-LPM-LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM3QM0 3QMu-QMPu-QM)4QM,)4QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @6v  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @6v  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @6v   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Yy b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOM[OMT[OMOMOMOMOMPM(PM=EPM=EPM-LPM-LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PMPM8 PM3-QMX3-QM)4QM4)4QM-QM-QMRM,RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 V  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 V  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_4  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 V   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1vr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1GU8x } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOM[OMT[OMOMOMOMOM!PM(!PMDPMDPM-LPM-LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PMWQM0 WQM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @6v bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @6v bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @6v  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y( b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`8h(h } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOM[OMT[OMOMOMOMOMPM(PM=EPM=EPM-LPM-LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM, QM.QML.QM5QM$5QMQMQMwRMwRMORMORMSMSMMTMMTMTUMTUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 VRRGg b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1c*q } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>)?)IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpYqYssu=v=xxz!{!}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM[OM[OMOMLOMaOMTaOMOMOM!OM!OM-PM(-PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM!QM0 !QMc-QMPc-QM)4QM,)4QM7QM7QMRM$RMsRMsRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 #c5u bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 #c5u bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 #c5u  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1cF)@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMcPM cPMQM8 QM-QMX-QM)4QM4)4QMQMQM}RM,}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T)  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1kgnHh b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1R$v } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?Q@QBBD7E7GGIJLLNOQvQvSSU\V\XXZB[B]]_(`(bbdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM[OM[OMOMLOMaOMTaOMOMOM!OM!OM'PM('PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM PM  PMEQM0 EQM-QMP-QM6QM,6QMُQMُQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 "b5u bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 "b5u bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 "b5u  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 oR5# } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)>*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMiPM iPMQM, QM.QML.QM5QM$5QMQMQMkRMkRMCRMCRM}SM}SMTMTMSUMSUMefUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 X  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 X  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 X   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 KGGKk b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Hl>"b } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  QQ)7*744>?IISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?/@/BBDEGGIIKdLdNNPFQFSSU(V(XXZ [ ]{]{__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMӚOMӚOMqOMqOMOM$OMPMPMCEPMCEPMiIPM$iIPMwnPMwnPMPMPM;PM$;PMPMPMPMPM1QM 1QMQM| QMRM RMRM RMSM SMTM TMTUMTUM[gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1EyM3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1EyM3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1EyM3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdnenggiXjXllnBoBqqs,t,vvxy{{}~uu__ԇԉII33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMgOMgOMPMPM1EPM1EPM9LPM9LPMenPMpenPMPMPM PM PMiPM`iPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Dd  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  aa)K*K44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44!!   ""$j%j'')T*T,,.>/>113(4(6689;;==?q@qBBD[E[GGIDJDLLN,O,QQSTVVXXZp[p]]_X`Xbbd@e@ggi(j(llnoqqssulvlxxzT{T}}<<$$ ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMٚOMٚOMwOMwOMOM$OMPMPMCEPMCEPMiIPM$iIPMwnPMwnPMPMPM;PM$;PMPMPMPMPM1QM 1QMQM| QMRM RMmRM mRMSM SMwTM wTMGTUMGTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1FzK6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1FzK6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1FzK6 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)L*L44>4?4IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI8J8LLNOQQSTVwVwXXZ][]]]_C`Cbbd)e)ggijllnnphqhssuNvNxxz4{4}}ssYY̎̐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMgOMgOMPMPM1EPM1EPM9LPM9LPMenPMpenPMPMPM PM PMoPM`oPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Mm  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  __)I*I44>1?1IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI1J1LLNOQQSSUpVpXXZV[V]]_<`v>xxz"{"}}xx\\ωϋBB(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMmOMmOM OM  OMOMOM?PM?PMDPMDPMIPMIPMnPMpnPMPMPMYPMYPMcPM`cPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1#c} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1#c} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1#c  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ee  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  gg)S*S44>;?;IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG77##  "#%%'')q*q,,.]/]113I4I668595;;=>@@BCE{E{GGIcJcLLNKOKQQS3T3VVXY[[]^`w`wbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOM=OM=OMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPM]PM`]PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1=]  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>:?:IIS(T(^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGIbJbLLNPOPQQS>T>VVX,Y,[[]^``bceeggimjmllnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMgOMgOMOM OMOMOM9PM9PMDPMDPMIPMIPM nPMp nPMPMPMYPMYPMoPM`oPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SM;TMT ;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1"b} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1"b} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1"b  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  aa)I*I44>-?-IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55!!  } }""$e%e'')M*M,,.5/511346689;y;y==?]@]BBDAEAGGI%J%LLN O Q{Q{SSU_V_XXZC[C]]_'`'bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOM=OM=OMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMoPM`oPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ZZ)D*D44>.?.IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppZZ D D  ..wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD^  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ee)W*W44>G?GIIS3T3^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssee W W  II;;--  "#%%'(*|*|,,.n/n113`4`668R9R;;=D>D@@B6C6EEG(H(JJLMOOQRT{T{VVXiYi[[]W^W``bCcCeeg-h-jjlmooqqsptpvvxVyV{{}<~<""xx\\ΑΓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMgOMgOMPMPM=EPM=EPM9LPM9LPMqnPMpqnPMPMPM PM PMWPM`WPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations18X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  dd)P*P44>:?:IIS"T"^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@44((  "#%%'(*~*~,,.j/j113V4V668B9B;;=.>.@@BCEEGHJzJzLLNbObQQSJTJVVX2Y2[[]^``bcevevggi^j^llnFoFqqs.t.vvxy{{}}rrZZ·ΉBB** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMaOMaOMOM OMOMOM3PM3PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMiPM`iPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS!T!^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbddedggiJjJlln.o.qqstvvxxzc{c}}EE''yy[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMgOMgOMPMPM=EPM=EPM9LPM9LPMqnPMpqnPMPMPM PM PMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Mm  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)H*H44>.?.IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00    "#%t%t'')\*\,,.D/D113,4,6689;;==?p@pBBDXEXGGI>J>LLN"O"QQSTVxVxXXZ\[\]]_@`@bbd$e$ggijlzlznnp^q^ssuBvBxxz&{&}} ||``҉ҋDD(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM-PM-PMDPMDPMIPMIPMmPMpmPMPMPMePMePMQPM`QPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1:z} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1:z} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1:z  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations19Y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  __)O*O44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??//  ""$w%w'')g*g,,.W/W113G4G668797;;='>'@@BCEEGHJ}J}LLNiOiQQSUTUVVXAYA[[]-^-``bceeghj{j{llngogqqsStSvvx?y?{{}+~+yyeeۑۓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM%OM%OMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMɵPMɵPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  TT)>*>44>$?$IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiUU A A  --yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPMIPMIPMmPMpmPMPMPMkPMkPMiPM`iPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1;{} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1;{} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1;{  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)E*E44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$W%W'')C*C,,.///11346689;};}==?i@iBBDUEUGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77{{cc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM%OM%OMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMɵPMɵPMPM`PMPMPM1QM1QMQML QMeRM eRM=RMp =RMwSMt wSMTMT TMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  TT):*:44>?IISS]o^ohhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //ww] ]""$C%C''))*),,./11335h6h88:N;N==?0@0BBDEGGIIKeLeNNPGQGSSU)V)XXZ [ ]|]|__a^b^ddf@g@iik"l"nnpqsusuuuwWxWzz|9}9kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM'PM'PMDPMDPMiIPMiIPMmPMpmPMPMPM;PM;PMEPM`EPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations12R  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbdbebggiLjLlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOM[OM[OMPMPMCEPMCEPM-LPM-LPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMYTUM YTUMgUM"} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7operation.6exchange :z2breasonOperatorInputsvalue8invocations1 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:p122prreasonvaluehhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv``ZkernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })zoutputElements"640zinput0Elements*6144zinput1Elements252488binvocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPMiIPMiIPMmPMpmPMPMPM;PM;PMcPM`cPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)@*@44>(?(IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$S%S'')=*=,,.'/'11346688:p;p==?Z@ZBBDDEDGGI,J,LLNOQQSSUkVkXXZQ[Q]]_7`7bbdeggijlvlvnnp\q\ssuBvBxxz({(}}ggډڋMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOM[OM[OMPMPMCEPMCEPM-LPM-LPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOOMOOMOM OMOMOM!PM!PMDPMDPMIPMIPMmPMpmPMPMPM_PM_PMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations17w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations17w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations17w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>/?/IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbdSeSggi;j;lln#o#qqs t vvxxzg{g}}OOÂÄ77uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMõPMõPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uJ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOOMOOMOM OMOMOMPMPMDPMDPMIPMIPMmPMpmPMPMPM_PM_PMPM`PMPMPM1QM1QMQML QMeRM eRM=RMp =RMwSMt wSM#TMT #TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations18x} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations18x} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations18x  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  UU)=*=44>!?!IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMõPMõPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tJ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMIOMIOMOM OMOMOMPMPMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>;?;IIS'T'^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMUOMUOMPMPMOEPMOEPM'LPM'LPMnPMpnPM!PM!PMPMPMcPM`cPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM]eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1Tx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  XX)D*D44>.?.IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44((  "#%%'')r*r,,.^/^113J4J668696;;=">"@@BCEEGGInJnLLNVOVQQS>T>VVX&Y&[[]^``bbdjejggiRjRllnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMIOMIOMOM OMOMOMPMPMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOOMOOMPMPMOEPMOEPM!LPM!LPMnPMpnPM!PM!PMPMPMPM`PMQMQM1QM1QMQMT QMkRM kRMRMx RMqSM| qSMGTM\ GTM=RUM=RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)<*<44>"?"IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI2J2LLNOQQSSUlVlXXZP[P]]_4`4bbdeggiiknlnnnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L OMCOMCOMOM OMOMOMPMPMDPMDPMIPMIPMmPMpmPMPMPMSPMSPM]PM`]PMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations14t} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations14t} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations14t  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1Nr  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)E*E44>3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqllnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L OMOMOMOM OMOMOMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMPMPMPM`PMPMPM1QM1QMQML QMqRM qRMRMp RMwSMt wSMATMT ATM7RUM7RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10]]  RR)<*<44>"?"IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1]]II 5 5  !!  wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbdeggiikplpnnpVqVssu'?'IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L OMOMOMOM OMOMOMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMPMPMPM`PMPMPM1QM1QMQML QM_RM _RMRMp RMeSMt eSMTMT TMQUMQUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  PP)6*644>?IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMOMOMOM|OM!OM!OMWOMWOMOM|OMOMHOMPMPMDPMPDPMIPMXIPM)MPM)MPMVPMPVPMYPMYPMmPMmPM[PM$ [PMųPM, ųPMPM PMPM$ PMPM PMPM| PMQPMXQPMQMQM-QM-QM;QM;QMkpQM\kpQMQMQMQMQMRM8RM[RM[RMSMSMSMSMTMlTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pk b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pk b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pk  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations17w%e  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d7n%\o$JY8o&]K L   9  p   ^   L  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10GG  UU)K*K44>7?7IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1GG;; / /  ==11%%  " # %%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnOoOqqs7t7vvxy{{}~{{ccׇ׉KK33# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMaEPMaEPM LPM LPMUPM@UPMXPM XPMnPMnPM3PM3PM۵PM ۵PMePM ePMPMd PMPM PMPM PMQMP QM.QMp.QM! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1>^nj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1R$Ix L  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dR$vHl> dV8! l ` 4   \  0  T 9<| bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)J*J44>@@BCEEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsqtqvvxWyW{{}=~=## {{__ёѓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMOMOMOM|OM!OM!OMWOMWOMOM|OMOMHOMPMPMDPMPDPMIPMXIPM)MPM)MPMVPMPVPMYPMYPMmPMmPM[PM$ [PMųPM, ųPMPM PMPM$ PMPM PMPM| PMKPMXKPMQMQM-QM-QMCx`-0b P   p  @   b  4T bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10FF  QQ)A*A44>)?)IIS T ^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1FF66 & &  11!! y y""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpeqessuIvIxxz-{-}}ggىًKK//# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMgEPMgEPM LPM LPMUPM@UPMXPM XPMnPMnPM9PM9PM۵PM ۵PMePM ePMPMd PMPM PMPM PMQQMP QQM-QMp-QME0?0IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$_%_'')M*M,,.;/;113)4)6689;;==?a@aBBDOEOGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ~~``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMCOMCOMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMKPM KPMQMH QM-QMh-QM?IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^JJ 6 6  ""nnX X""$B%B''),*,,,./11346u6u88:_;_==?-@-BBDEGGIJLLNNPlQlSSURVRXXZ8[8]]_`bbdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PM[EPM[EPMLPMLPMUPM@UPMXPM XPMnPMnPM-PM-PMPM PMqPM qPMPMd PMPM PM{PM {PMQMP QM-QMp-QMW9QMLW9QM}QM}QMQMQMQMQMeRMTeRM=RM=RMwSMwSMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1]}`\t b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 I@ b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<I[$m6HvZ?Q  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)D*D44>4?4IIS T ^^hisjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln`o`qqsLtLvvx8y8{{}$~$XXΌΎDD  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OM=OM=OMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMWPM WPMQMH QM-QMh-QM3((  _    t M  g  Z )  M@j] bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  II)/*/44>?IISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$llR R""$8%8'')*,,./1w1w335]6]88:C;C==? @ B}B}DDF_G_IIK\L\NNP>Q>SSU V XXZ[]s]s__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMqPM qPMPMd PMPM PM9PM 9PMuQMP uQM-QMp-QM;QML;QMQMQM7QM7QM5QM5QMSRMTSRM+RM+RMeSMeSMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations12R{' b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 7w  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<7n%\J8/f  c , u Y bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>&?&IIST^^hhrSsS} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqzqzssubvbxxzJ{J}}22ss[[ώϐCC  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMIOMIOMOMdOMUOMlUOMOMOMOMOMPM@PMDPMDPM'LPM'LPMUPM@UPMXPM XPMmPMmPMPMPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM9QMD9QM|QM|QMuQMuQMsQMsQMSRMLSRM+RM+RMeSMeSMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T7w bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T7w bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T7w  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 cJ= b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<cF) oR5S {F^  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)8*844>#?#IIS T ^^hhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!m m""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI3J3LLNOQQSTVwVwXXZ_[_]]_G`Gbbd/e/ggijllnnpsqsssu[v[xxzC{C}}++ooYYΎΐCC  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMUOMTUOMOMOMOMOMPM(PMUEPMUEPM'LPM'LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMcPM cPMQM8 QM-QMX-QME9QM4E9QMQMQM}RM,}RMURMURMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ] bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ] bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\(  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1XxJFNr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1/o bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Y g.  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMCOMCOMOMdOMOOMlOOMOMOMOMOMPM@PMDPMDPM!LPM!LPMUPM@UPMXPM XPMmPMmPMPMPMPM PM}PM }PMPMd PMPM PMKPM KPMQMH QM-QMh-QM;QMD;QM;QM;QMQMQMQMQMARMLARMRMRMSSMSSMSMSMTMTMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U7w bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U7w bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U7w  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  +Dd b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 <|v  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<<x4p,h$`\8 q * c  G  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL)6*644> ? IIST^w^whhrBsB} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikelennpIqIssu-v-xxz{}}ggلن22  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMUEPMUEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMKPM KPMQM8 QM-QMX-QM;QM4;QM QM QMkRM,kRMCRMCRM}SM}SMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ^ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ^ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ^  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1dCc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1u <  J &f } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMIOMIOMOMLOMaOMTaOMOMOM!OM!OMPM(PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM9QM,9QMQMQM}RM$}RMURMURMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 5u9y  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 5u9y  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 5u9y   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8Ss b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations18 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1ZP   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIUJULLNCOCQQS1T1VVXY[[] ^ ``bbdrerggi`j`llnIoIqqs-t-vvxy{{}}ggقلKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PM?PM ?PM{QM8 {QM-QMX-QM99QM499QMYQMYQM}RM,}RMURMURMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 h. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 h. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 h.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1401U b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1^ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<F n  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMIOMIOMOMLOMaOMTaOMOMOM!OM!OMPM(PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM;QM,;QM QM QMkRM$kRMCRMCRM}SM}SMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 4t8x bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 4t8x bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 4t8x  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1s  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1F  < w # c  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>!?!IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMPM PM-QM8 -QMo-QMXo-QM;QM4;QMݎQMݎQMeRM,eRM=RM=RMwSMwSMTMTMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 i0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 i0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 i0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1}~V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P  Z  3 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMOMTOMOMOMEOMEOM!PM(!PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PMcPM cPMQM0 QM-QMP-QM'9QM,'9QM#QM#QMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IO@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IO@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IO@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 wPp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T\4 t  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  YY)E*E44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')s*s,,._/_113K4K668797;;=#>#@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMgOMTgOMOMOM'OM'OMPM(PMIEPMIEPM9LPM9LPMUPM(UPMXPMXPM}nPM}nPMPMPM PM  PMPM PMPML PM PM  PM-PM -PMiQM8 iQM-QMX-QM-9QM4-9QM)QM)QMRM,RMgRMgRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 h " bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 h " bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 h "  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1> b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 M bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1b%h= }  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  ZZ)L*L44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhZZ L L  >>00""  "#%%'')q*q,,.c/c113U4U668G9G;;=9>9@@B+C+EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3qqUUǑǓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMOMTOMOMOMEOMEOM!PM(!PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM;QM,;QMQMQMkRM$kRMCRMCRM}SM}SMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JN> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JN> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JN>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x?_ @ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 d ( l  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)=*=44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMIEPMIEPM?LPM?LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMPM PM!QM8 !QMc-QMXc-QM;QM4;QMQMQM}RM,}RMURMURMSMSMwTMwTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 i $ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 i $ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 i $  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1zvvN b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1+ n 1 t  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMUOMTUOMOMOMOMOM'PM('PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM3QM0 3QMu-QMPu-QM?9QM,?9QMQMQMqRM$qRMIRMIRMSMSMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 *j7w  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 *j7w  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 *j7w   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 j b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1h7U : } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbdeg{g{iikalannpGqGssu-v-xxz{}}ll߄߆RRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMUOMTUOMOMOMOMOMPM(PMCEPMCEPM'LPM'LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMWQM8 WQM-QMX-QM99QM499QMQMQMRM,RMsRMsRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h;  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1|( b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1R bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1HV  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>8?8IIS$T$^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJxJxLLNdOdQQSPTPVVX?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMUOMTUOMOMOMOMOMPM(PMCEPMCEPM'LPM'LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMQM8 QMW-QMXW-QM;QM4;QMQMQMRM,RM[RM[RMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1sooG{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d + r 9 Y } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)>*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOM[OMT[OMOMOMOMOM-PM(-PMDPMDPM-LPM-LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM!QM0 !QMc-QMPc-QMW9QM,W9QMQMQMRM$RM[RM[RMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @8x  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @8x  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @8x   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]} b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations10p bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@tN  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOM[OMT[OMOMOMOMOMPM(PM7EPM7EPM-LPM-LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PM PM  PMEQM8 EQM-QMX-QMQ9QM4Q9QMOQMOQMRM,RMgRMgRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]0  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1r b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1(h bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 rD X } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKlln5o5qqstvvx y {~{~}}hh݂݄RRLJlj<<&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOM[OMT[OMOMOMOMOM'PM('PMDPMDPM-LPM-LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PMKQM0 KQM-QMP-QM;QM,;QMQQMQQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @8x bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @8x bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @8x  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(  \ 6 Z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOM[OMT[OMOMOMOMOMPM(PM=EPM=EPM-LPM-LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PM QM8  QMK-QMXK-QM;QM4;QMߏQMߏQM}RM,}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1lhh@k b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 h : ^ * } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)=*=44>'?'IIS T ^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnp[q[ssuAvAxxz'{'}} ffىًLL22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMaOMaOMOMLOMaOMTaOMOMOM!OM!OM-PM(-PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QMQ-QMPQ-QMu9QM,u9QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _7w bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _7w bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _7w  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1F bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1}b G  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOMaOMTaOMOMOM!OM!OMPM(PM1EPM1EPM3LPM3LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM8 QM-QMX-QMi9QM4i9QMQMQMRM,RMgRMgRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R% b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R% b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R%  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1fKk b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1>~ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xU2  ^ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<,,  "#%z%z'')f*f,,.R/R113>4>668*9*;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM[OM[OMOMLOMaOMTaOMOMOM!OM!OM-PM(-PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM?QM0 ?QM-QMP-QM%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMoPM oPMQM8 QM-QMX-QM *>44>$?$IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**r r""$Z%Z'')B*B,,.*/*11346688:n;n==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp>  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOMkOMOM$OMPMPM=EPM=EPMiIPM$iIPMqnPMqnPMPMPM;PM$;PMPMPMPMPM1QM 1QMQM| QMRM RMRM RMSM SMTM TMTUMTUM[gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1AuO- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1AuO- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1AuO- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  nn)Z*Z44>D?DIIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ>>22  "&#&%%'(**,,.t/t113`4`668L9L;;=8>8@@B$C$EEGHJJLLNlOlQQSTTTVVXI?IIIS5T5^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uugg Y Y  KK==//!!  "#%%'(*~*~,,.p/p113b4b668T9T;;=F>F@@B8C8EEG*H*JJLMOOQRT}T}VVXkYk[[]Y^Y``bEcEeeg/h/jjlmooqqsrtrvvxXyX{{}>~>$$zz^^БГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMӚOMӚOMqOMqOMOM$OMPMPMCEPMCEPMiIPM$iIPMwnPMwnPMPMPM;PM$;PMPMPMPMPM1QM 1QMQM| QMRM RMmRM mRMSM SMkTM kTM;TUM;TUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1BvM0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1BvM0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1BvM0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)P*P44>6?6IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%|%|'')d*d,,.L/L1134446689;;=>@x@xBBD`E`GGIFJFLLN*O*QQSTVVXXZd[d]]_H`Hbbd,e,ggijllnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMaOMaOMPMPM1EPM1EPM3LPM3LPMenPMpenPMPMPMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 } bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1   bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  cc)Q*Q44>=?=IIS%T%^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uucc Q Q  ??--   ""$n%n'')\*\,,.J/J113848668&9&;;=>@@BCEyEyGGIeJeLLNOOOQQS9T9VVX#Y#[[] ^ ``bbdhehggiNjNlln2o2qqstvvxxzg{g}}II++ }}__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMsOMsOMOM OMOMOMEPMEPMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMiPM`iPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1_} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1_} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1_  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Hh  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ^^)H*H44>.?.IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##m m""$W%W'')A*A,,.+/+11346688:t;t==?Z@ZBBD@E@GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpVqVssu^  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  aa)Q*Q44>???IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11!!  "#%y%y'')i*i,,.Y/Y113I4I668999;;=)>)@@BCEEG H JJLLNkOkQQSWTWVVXCYC[[]/^/``bceeghj}j}llnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMmOMmOM OM  OMOMOM?PM?PMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMiPM`iPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1^} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1^} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1^  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ii  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  \\)B*B44>$?$IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##  e e""$K%K'')1*1,,./11335p6p88:V;V==?8@8BBDEGGIIKmLmNNPOQOSSU1V1XXZ[]]__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMǚOMǚOMeOM eOM=OM=OMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMoPMoPMQMQM1QM1QMQMQMRM RMmRM2 mRMSMR SMTM*TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" boperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r72w5:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])I*I44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$[%['')G*G,,.3/31134668 9 ;;==?m@mBBDYEYGGICJCLLN+O+QQSTVVXXZo[o]]_W`Wbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMmOMmOM OM  OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PM]PM`]PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  __)I*I44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22  ~ ~""$h%h'')R*R,,.e>ggi&j&llnoqqssujvjxxzR{R}}::"" jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMaOMaOMPMPM7EPM7EPM3LPM3LPMknPMpknPM PM PMPMPMWPM`WPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations19Y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>5?5IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI]J]LLNGOGQQS1T1VVXY[[]^`z`zbbddedggiNjNlln8o8qqs"t"vvx y {{}}kkUUʇʉ??)) b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMgOMgOMOM OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PMoPM`oPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Rr  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>-?-IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?[@[BBDEEEGGI-J-LLNOQQSSUlVlXXZR[R]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXˉˋ>>$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMaOMaOMPMPM7EPM7EPM3LPM3LPMknPMpknPM PM PMPMPMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ZZ)D*D44>,?,IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  l l""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI0J0LLNOQQSSUoVoXXZU[U]]_;`;bbd!e!ggijlzlznnp`q`ssuFvFxxz,{,}}kkމދQQĎĐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMePMePMWPM`WPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations16v} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations16v} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations16v  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1<\  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>8?8IIS&T&^^h i s|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI`J`LLNNONQQS1?1IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==--  "#%{%{'')g*g,,.S/S113?4?668+9+;;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99ww b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMePMePMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations17w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations17w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations17w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Qq  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  VV)@*@44>*?*IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llVV @ @  **ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLN O QQSSUkVkXXZU[U]]_?`?bbd)e)ggijllnnplqlssuPvPxxz4{4}}nnRRĎĐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOM%OM%OMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMɵPMɵPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)A*A44>%?%IIS T ^{^{hhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==-- u u""$]%]'')E*E,,.-/-11346688:q;q==?U@UBBD9E9GGIJLLNOQsQsSSUWVWXXZ;[;]]_`bbdeguguiikYlYnnp=q=ssu!v!xxz{}w}w[[̈́͆== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPMiIPMiIPMmPMpmPMPMPM;PM;PMKPM`KPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations15U  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>22&&  "#%%'(*|*|,,.h/h113T4T668@9@;;=,>,@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM[OM[OMPMPMCEPMCEPM-LPM-LPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  [[)M*M44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii[[ M M  ??11##  "#%%'')r*r,,.d/d113V4V668H9H;;=:>:@@B,C,EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM'PM'PMDPMDPMiIPMiIPMmPMpmPMPMPM;PM;PMiPM`iPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Rr  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)D*D44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$p%p'')X*X,,.@/@113(4(6689;;==?l@lBBDTETGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMUOMUOMPMPMCEPMCEPM'LPM'LPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPMIPMIPMmPMpmPMPMPMYPMYPMPM`PMPMPM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations13s} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations13s} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations13s  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>"?"IIST^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sF b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMUOMUOMOM OMOMOM!PM!PMDPMDPMIPMIPMmPMpmPMPMPMYPMYPMPM`PMPMPM1QM1QMQML QMYRM YRM1RMp 1RMkSMt kSMہTMT ہTMSUMSUMSfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations14t} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations14t} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations14t  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]k^khhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOOMOOMOM OMOMOM!PM!PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>&?&IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOOMOOMPMPMOEPMOEPM!LPM!LPMnPMpnPM!PM!PMPMPMiPM`iPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM]eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1Uy  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>)?)IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIQJQLLN;O;QQS%T%VVXY[[]]_n`nbbdXeXggiBjBlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMIOMIOMOM OMOMOMPMPMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SM;TMT ;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOOMOOMPMPMOEPMOEPM!LPM!LPMnPMpnPM!PM!PMPMPMPM`PMQMQM1QM1QMQMT QMqRM qRMRMx RMwSM| wSMSTM\ STMIRUMIRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844> ? IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM?eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)G*G44>/?/IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11!!   ""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMCOMCOMOM OMOMOMPMPMDPMDPM{IPM{IPMmPMpmPMPMPMMPMMPMuPM`uPMQMQM1QM1QMQMT QMwRM wRMRMx RM}SM| }SMYTM\ YTMORUMORUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations11q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations11q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations18l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations11q  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1g  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)8*844>"?"IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnppqpssuTvTxxz8{8}}rrVVȎȐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMkRM kRMRMp RMqSMt qSM)TMT )TMRUMRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)=*=44>!?!IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!  i i""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMOMOMOM|OM!OM!OMWOMWOMOM|OMOMHOMPMPMDPMPDPMIPMXIPM)MPM)MPMVPMPVPMYPMYPMmPMmPMaPM$ aPMųPM, ųPMPM PMPM$ PMPM PMPM| PMuPMXuPMQMQM-QM-QM;QM;QMwpQM\wpQMQMQMQMQMRM8RMmRMmRMSMSM!SM!SMTMlTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pm b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pm b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pm  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1)i9y+k  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d)9rn+3dxVH:t-f   X   C z  5 u  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10CC  OO)I*I44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1CC33 # #  //w w""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllnoooqqs[t[vvxGyG{{}3~3 mm# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMaEPMaEPM LPM LPMUPM@UPMXPM XPMnPMnPM3PM3PM۵PM ۵PMePM ePMPMd PMPM PMQPM QPMQMH QM-QMh-QM;QMD;QMpQMpQMCQMCQMAQM AQM}RM}RMURMpURMSMtSM SMT SMTMTM}TUM$}TUM%gUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 E bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 E bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 E  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Mm?_ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations11qGW  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d1G|UGc*q8J\  % n 7    ! N  ` bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)@*@44>0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;==?^@^BBDLELGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnXoXqqs>""  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMOMOMOM|OM!OM!OMWOMWOMOM|OMOMHOMPMPMDPMPDPMIPMXIPM)MPM)MPMVPMPVPMYPMYPMmPMmPM[PM$ [PMųPM, ųPMPM PMPM$ PMPM PMPM| PM?PMX?PM{QM{QM-QM-QME+?+IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1BB..    ##qq] ]""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoqqssuovoxxzW{W}}??''kk# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMaEPMaEPM LPM LPMUPM@UPMXPM XPMnPMnPM3PM3PM۵PM ۵PMePM ePMPMd PMPM PMoPM oPMQMH QM-QMh-QMr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1R$tD  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dR$vH](ls>>`0 P   p  @   b l  4T bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)8*844>$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$?%?''))*),,./11335r6r88:\;\==?)@)BBDEGGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMIOMIOMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PM{PM {PMQMH QM-QMh-QM;QMD;QM}pQM}pQM#QM#QM!QM !QM}RM}RMURMpURMSMtSM SMT SMTMTMTUM$TUM1gUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 <|9y bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 <|9y bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 <|9y  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations19y"b+k  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d9"ri+0dwVL>w0i  " [    H   : z  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  MM);*;44> ? IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGI5J5LLNOQQS T VVXY[[]]_n`nbbdXeXggiBjBlln6o6qqs t vvx y {{}}iiނބSSȇȉ==''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PM[EPM[EPMLPMLPMUPM@UPMXPM XPMnPMnPM-PM-PMPM PMqPM qPMPMd PMPM PMiPM iPMQMH QM-QMh-QM5QMD5QMyQMyQMQMQMQMQMYRMLYRM1RM1RMkSMkSMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Aab b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 H,l b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<H,uX> h0x@P  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  ZZ)F*F44>2?2IIST^^his\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln@o@qqs(t(vvxy{{}}llTT ||  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMCOMCOMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMEPM EPMQMH QM-QMh-QM;QMD;QM}pQM}pQMQMQMQM QMkRMkRMCRMpCRM}SMt}SMSMTSMMTMMTMTUM$TUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ;{9y bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ;{9y bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ;{9y  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations19y+k  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d9r+d>WLI;t-f   X   C   [ 5 u  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  LL)6*644>?IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGIJLzLzNNP`Q`SSUcVcXXZI[I]]_/`/bbdeggiiknlnnnp\q\ssuBvBxxz({(}}ggډڋMM33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PM[EPM[EPMLPMLPMUPM@UPMXPM XPMnPMnPM-PM-PMPM PMwPM wPMPMd PMPM PMuPM uPMQMH QM-QMh-QM6QMD6QMszQMszQM)QM)QM'QM'QMARMLARMRMRMSSMSSMSMSMTMTMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Aat b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 9y b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<9r+dPXbJ+C|E  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)<*<44>$?$IIST^~^~hhrEsE} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpXqXssu)?)IIST^^hhrQsQ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33##  ""$q%q'')]*],,.I/I113545668!9!;;= > @@BBDiEiGGIQJQLLN9O9QQS!T!VVX Y [}[}]]_e`ebbdMeMggi5j5llnoqqstvyvyxxza{a}}II11ooUU  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMUEPMUEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM;4QM,;4QMuQMuQMeRM$eRM=RM=RMwSMwSM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 3S b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1_ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1f-t  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMIOMIOMOMdOMUOMlUOMOMOMOMOMPM@PMDPMDPM'LPM'LPMUPM@UPMXPM XPMmPMmPMPMPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM6QMD6QMgzQMgzQMQMQMQMQM;RML;RMRMRMMSMMSMSMSMTMTMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U9y bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U9y bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U9y  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  <\ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 G b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<GUc=*qO8F2 r  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)7*744>?IIST^s^shhr:s:} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$S%S'');*;,,.#/#113 4 6688:g;g==?M@MBBD1E1GGIJLLNNPkQkSSUOVOXXZ3[3]]_`bbddfmgmiikQlQnnp5q5ssuvxxzz|o}oSSńņmmސޒ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMUEPMUEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQMSRM$SRM+RM+RMeSMeSMՁTMՁTMSUMSUMMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 \ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 \ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 \  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1;I V  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  LL)2*244>?IISS]i^ihhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ooU U""$;%;'')!*!,,./1z1z335`6`88:F;F==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3gg׋׍GG b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMgOMTgOMOMOM'OM'OM!PM(!PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PMcPM cPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 1q;{  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 1q;{  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 1q;{   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 HhXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1[&q  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>9?9IIS%T%^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMOOQQSmTmVVX[Y[[[]I^I``b5c5eeghjjl m o|o|qqsbtbvvxHyH{{}.~.llތގPP‘“ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM/4QM,/4QMKQMKQMwRM$wRMORMORMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 f. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 f. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 f.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }!A b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1R bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Wab  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOOMOOMOMLOMaOMTaOMOMOM!OM!OM!PM(!PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QM5QM5QMwRM$wRMORMORMSMSMqTMqTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 0p:z bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 0p:z bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 0p:z  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 %E"B b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<RK  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln"o"qqstvuvuxxzW{W}}99ooQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMύQMύQMkRM$kRMCRMCRM}SM}SMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 g0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 g0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 g0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1&k0u '  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>#?#IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikhlhnnpLqLssu0v0xxz{}}jj܄܆PPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMOMTOMOMOMKOMKOM'PM('PMDPMDPM]LPM]LPMUPM(UPMYPMYPMmPMmPMPMPM/PM /PMPM PMPML PM1PM 1PMcPM cPMQM0 QM-QMP-QM)4QM,)4QMÍQMÍQMRM$RMgRMgRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IQ@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IQ@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IQ@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 QqBb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1G bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T!n   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)C*C44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')[*[,,.K/K113;4;668+9+;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMQQM0 QQM-QMP-QM)4QM,)4QM!QM!QMRM$RM[RM[RMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 f" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 f" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 f"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 m * b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1E bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1H N5 u  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMOMTOMOMOMEOMEOM!PM(!PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM6QM,6QMSQMSQM}RM$}RMURMURMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JP> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JP> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JP>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 |@`1 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1;U"d  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$M%M'')9*9,,.%/%11346688:s;s==?_@_BBDKEKGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMIEPMIEPM?LPM?LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 g$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 g$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 g$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1TZ  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM#4QM,#4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 &f9y  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 &f9y  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 &f9y   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Jj.N b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Q"s `  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln0o0qqstvvxy{y{y}}cc؂؄MM‡‰77!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PMKQM0 KQM-QMP-QM#4QM,#4QMoQMoQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f7  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1I[  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJvJvLLN^O^QQSFTFVVX.Y.[[]^``bbdrerggiZjZllnBoBqqs*t*vvxy{{}}nnVVʇʉ>>&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM'PM('PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 %e9y  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 %e9y  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 %e9y   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 oAa b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Df7  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}cc։֋II// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$m6 I  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)@*@44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$l%l'')T*T,,.>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOM[OMT[OMOMOMOMOM-PM(-PMDPMDPM-LPM-LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM)4QM,)4QMŎQMŎQMRM$RMaRMaRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @:z  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @:z  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @:z   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1\8  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMǚOMǚOMeOMLeOM[OMT[OMOMOMOMOMPM(PM7EPM7EPM-LPM-LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM)4QM,)4QM#QM#QM}RM$}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[,  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 _Ss b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T(|0 p  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMaOMTaOMOMOM!OM!OM-PM(-PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMPM PM9QM0 9QM{-QMP{-QM6QM,6QMaQMaQMqRM$qRMIRMIRMSMSM/TM/TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @:z bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @:z bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @:z  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pL(l } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>!?!IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOM[OMT[OMOMOMOMOMPM(PM7EPM7EPM-LPM-LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQMeRM$eRM=RM=RMwSMwSMTMTMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Dd> b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P$xL  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]m^mhhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?.@.BBDEGGIIKcLcNNPEQESSU'V'XXZ [ ]z]z__a\b\ddf>g>iik l nnpqssssuuwUxUzz|7}7kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMaOMTaOMOMOM!OM!OM3PM(3PMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMPM PMQQM0 QQM-QMP-QM/4QM,/4QMyQMyQMRM$RMsRMsRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [9y bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [9y bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [9y  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1gN5 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OMaOMTaOMOMOM!OM!OMPM(PM1EPM1EPM3LPM3LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM/4QM,/4QM׎QM׎QMRM$RMgRMgRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P!  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 XxNn b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1_>  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  WW)A*A44>,?,IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::** v v""$`%`'')J*J,,.4/411346689;};}==?g@gBBDQEQGGI1?1IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OMaOMTaOMOMOM!OM!OMPM(PM1EPM1EPM3LPM3LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMyQMyQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x ,Uu b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1|[: } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>'?'IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnTTljNj::  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOMkOMOM$OMPMPM7EPM7EPMiIPM$iIPMknPMknPM PM PM;PM$;PMPMPM PM PM1QM 1QMQM| QMRM RMRM RMSM SMTM TMTUMTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=qQ' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=qQ' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=qQ' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)X*X44>F?FIIS2T2^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%%'')p*p,,.`/`113P4P668@9@;;=0>0@@B C EEGHJJLLNrOrQQS^T^VVXJYJ[[]6^6``b"c"eeghjjllnpopqqs\t\vvxHyH{{}4~4  nn b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOMaOMaOMPMPM+EPM+EPM3LPM3LPM_nPMp_nPMPMPMPMPMoPM`oPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ff  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>=?=IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIeJeLLNSOSQQSATAVVX/Y/[[]^``b c eeggipjpllnYoYqqs=t=vvx!y!{{}~ww[[͇͉??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOMkOMOM$OMPMPM=EPM=EPMiIPM$iIPMqnPMqnPMPMPM;PM$;PMPMPM PM PM1QM 1QMQM| QMRM RMyRM yRMSM SMTM TMwTUMwTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>rO* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>rO* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>rO* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$`%`'')L*L,,.8/8113$4$6689;;==?r@rBBD^E^GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOMaOMaOMPMPM+EPM+EPM3LPM3LPM_nPMp_nPMPMPMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ]])G*G44>1?1IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss]] G G  11zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUrVrXXZ\[\]]_F`Fbbd0e0ggijllnoqsqsssuWvWxxz;{;}}uuYYˎː== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMyOMyOMOM OMOMOMEPMEPMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1[} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1[} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1[  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdkekggiUjUlln?o?qqs)t)vvxy{{}}rr\\чщFF00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM7OM7OMPMPM1EPM1EPM LPM LPMenPMpenPMPMPM۵PM۵PMcPM`cPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1?_  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  gg)S*S44>=?=IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC77++  "#%%' ( **,,.m/m113Y4Y668E9E;;=1>1@@BCEEG H J}J}LLNeOeQQSMTMVVX5Y5[[]^``bceyeyggiajallnIoIqqs1t1vvxy{{}~uu]]чщEE-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMsOMsOMOM OMOMOMEPMEPMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Z} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Z} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Z  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)I*I44>1?1IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI5J5LLNOQQSTVtVtXXZZ[Z]]_@`@bbd&e&ggi j llnnpeqessuKvKxxz1{1}}ppVVɎɐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM=OM=OMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Pp  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)K*K44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33##  "#%w%w'')_*_,,.G/G113/4/6689;;==?s@sBBD[E[GGIAJALLN%O%QQS T V{V{XXZ_[_]]_C`Cbbd'e'ggi j l}l}nnpaqassuEvExxz){)}} ccՉՋGG++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMsOMsOMOM OMOMOM?PM?PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMcPM`cPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Dd  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)P*P44>8?8IIS T ^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD44   " # %%'')n*n,,.Z/Z113F4F668292;;=>@@BCExExGGI`J`LLNHOHQQS0T0VVXY[[]^`t`tbbd\e\ggiDjDlln,o,qqstvvxxzp{p}}XX̂̄@@%% ~~ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMaOMaOMPMPM7EPM7EPM3LPM3LPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  WW)A*A44>'?'IIS T ^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llXX D D  00||f f""$P%P''):*:,,.$/$11346688:m;m==?S@SBBD9E9GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiikilinnpOqOssu5v5xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMmOMmOM OM  OMOMOM?PM?PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMiPM`iPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM;TMT ;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Mm  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ^^)F*F44>*?*IIST^^hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22 z z""$b%b'')J*J,,.2/211346689;v;v==?Z@ZBBD>E>GGI"J"LLNOQxQxSSU\V\XXZ@[@]]_$`$bbdegzgziik^l^nnpBqBssu&v&xxz { }|}|``҄҆BB$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOM[OM[OMPMPM7EPM7EPM-LPM-LPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  WW)=*=44>?IIST^r^rhhrRsR} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22zz` `""$F%F''),*,,,./11335k6k88:Q;Q==?3@3BBDEGGIIKhLhNNPJQJSSU,V,XXZ[]]__aabaddfCgCiik%l%nnpqsxsxuuwZxZzz|<}<nnދލNN b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPMIPMIPM nPMp nPMPMPM_PM_PMWPM`WPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations12r} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations12r} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations12r  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1?_  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  bb)T*T44>D?DIIS0T0^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppbb T T  FF88**  "#%%'(*y*y,,.k/k113]4]668O9O;;=A>A@@B3C3EEG%H%JJLMOOQRTxTxVVXfYf[[]T^T``b@c@eeg*h*jjlmooqqsmtmvvxSyS{{}9~9uuYYˑ˓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOM%OM%OMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMɵPMɵPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  XX)B*B44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++ w w""$a%a'')K*K,,.5/51134668 9 ;~;~==?h@hBBDRERGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMePMePMoPM`oPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations13s} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations13s} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations13s  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Tt  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIST^^hispsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdaeaggiGjGlln+o+qqs t v~v~xxz`{`}}BB$$vvXX b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOM%OM%OMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMɵPMɵPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  VV)@*@44>(?(IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //{{e e""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikmlmnnpQqQssu5v5xxz{}}ooSSƉƋ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMQPM`QPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations18X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)L*L44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$t%t'')d*d,,.T/T113D4D668494;;=$>$@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM-PM-PMDPMDPMiIPMiIPMmPMpmPMPMPM;PM;PMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Uu  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$T%T'')@*@,,.,/,11346689;z;z==?f@fBBDRERGGI%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPMIPMIPMmPMpmPMPMPMYPMYPMEPM`EPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1/o} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1/o} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1/o  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations13S  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qB b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPMIPMIPMmPMpmPMPMPMYPMYPMiPM`iPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations10p} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations10p} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations10p  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Tt  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pB b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDlElGGITJTLLN?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?G@GBBD-E-GGIJLLNNPlQlSSURVRXXZ8[8]]_`bbdeggiikglgnnpMqMssu3v3xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOOMOOMOM OMOMOM!PM!PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMeRM eRM=RMp =RMwSMt wSM#TMT #TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44>?IIST^x^xhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMIOMIOMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMPMPMPM`PMWQMWQM1QM1QMQML QMYRM YRMRMp RM_SMt _SMہTMT ہTMQUMQUMydUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1/+  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]n^nhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?'@'BBD E GzGzIIK\L\NNP>Q>SSU V XXZ[]s]s__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOOMOOMOM OMOMOMPMPMDPMDPM{IPM{IPMmPMpmPMPMPMMPMMPMEPM`EPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1,l} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1,l} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1,l  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations14X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%}%}'')o*o,,.a/a113S4S668E9E;;=7>7@@B)C)EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m ooqqsotovvxUyU{{};~;!!ww[[͓͑ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM'eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  LL)@*@44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //  k k""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`MbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%%mm b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMIOMIOMOM OMOMOMPMPMDPMDPM{IPM{IPMmPMpmPMPMPMMPMMPMiPM`iPMQMQM1QM1QMQMT QM}RM }RMRMx RMSM| SM}TM\ }TMsRUMsRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1-m} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1-m} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:n b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1-m  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1Y}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)B*B44>.?.IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln/o/qqstvvxxzd{d}}FF(( zz\\ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMqRM qRMRMp RMwSMt wSMGTMT GTM=RUM=RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  JJ)<*<44>$?$IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD4?4IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1@@..    (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjglln\o\qqs@t@vvx$y${{}~zz^^ЇЉBB&&# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM7OMl7OMOMOMOMOMPM@PM[EPM[EPM LPM LPMUPM@UPMXPM XPMnPMnPM-PM-PM۵PM ۵PMePM ePMPMd PMPM PM]PM ]PMQMH QM-QMh-QM;QMD;QMpQMpQMQMQMQM QMRMRMgRMpgRMSMtSMSMTSMTMTMTUM$TUMmgUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 C bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 C bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 C  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 \|` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1<|6vu  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d<x4p,h$`\rXM  (  T   P  L   F  %e bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)E*E44>5?5IIS!T!^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$m%m'')]*],,.M/M113=4=668-9-;;==?w@wBBDgEgGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjsllnkokqqsWtWvvxCyC{{}/~/}}iiߑߓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OMOMOMOM|OM'OM'OM]OM]OMOM|OMOMHOMPMPMDPMPDPMIPMXIPM/MPM/MPMVPMPVPMYPMYPMmPMmPMaPM$ aPM˳PM, ˳PMPM PMPM$ PMPM PMPM| PMoPMXoPMQMQM-QM-QMu 3 $   pG&f  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10??  HH):*:44>&?&IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1??))    {{eeO O""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnoqtqtssuXvXxxz<{<}} vvZZ̎̐>># b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM7OMl7OMOMOMOMOMPM@PMaEPMaEPM LPM LPMUPM@UPMXPM XPMnPMnPM3PM3PM۵PM ۵PMePM ePMPMd PMPM PMiPM iPMQMH QM-QMh-QM!)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$O%O'');*;,,.'/'11346688:u;u==?B@BBBD.E.GGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMIOMIOMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMQPM QPMQMH QM-QMh-QM;QMD;QMpQMpQMQMQMQM QMRMRM[RMp[RMSMtSMSMTSMTMTMTUM$TUM1gUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 8x;{ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 8x;{ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 8x;{  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1;{1q.n  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d;v1l'bXZN! hD/   : u 0  + f  ! \  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  VV)B*B44>?IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22&&  "#%%'')p*p,,.\/\113H4H668494;;= > @@B C EEGGIPJPLLN8O8QQS T VVX&Y&[[]^``bbdjejggiRjRllnDoDqqs,t,vvxy{{}}ppXẊ̉@@((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMUEPMUEPMLPMLPMUPM@UPMXPM XPMnPMnPM'PM'PMPM PMwPM wPMPMd PMPM PMoPM oPMQMH QM-QMh-QM9QMD9QM+}QM+}QMߏQMߏQMݚQMݚQMYRMLYRM1RM1RMkSMkSMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 N  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 N  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 N   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ej b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 Il b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<I[$n7I[6 h A > bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hisZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln2o2qqstvvxy{{{{}}eeڂڄOOzz  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMIOMIOMOMdOMCOMlCOMOMOMOMOMPM@PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMuPM uPMQMH QM-QMh-QM;QMD;QMpQMpQMQMQMQM QMkRMkRMCRMpCRM}SMt}SMSMTSMATMATMTUM$TUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 7w;{ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 7w;{ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1;o  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 7w;{  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1;{1q   b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d;v1l'bYO E v  = = y  4 K  / j  % ` 'g bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR):*:44>?IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$f%f'')N*N,,.6/611346689;z;z==?b@bBBDJEJGGIJLLNNPiQiSSUlVlXXZP[P]]_4`4bbdeggiiknlnnnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PM[EPM[EPMLPMLPMUPM@UPMXPM XPMnPMnPM-PM-PMPM PMwPM wPMPMd PMPM PMoPM oPMQMH QM-QMh-QM"?"IIST^^hhrFsF} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD?IIST^u^uhhr=s=} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$C%C'')-*-,,./11346v6v88:`;`==?H@HBBD.E.GGIJLLNNPmQmSSUSVSXXZ9[9]]_`bbdegxgxiik^l^nnpDqDssu*v*xxz{}}ii܄܆11  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OM[OMT[OMOMOMOMOMPM(PMOEPMOEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QMu9QM,u9QMQMQMwRM$wRMORMORMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 l b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1[ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1e< j   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOOMOOMOMdOMUOMlUOMOMOMOMOM!PM@!PMDPMDPM'LPM'LPMUPM@UPMXPM XPMmPMmPMPMPMPM PMPM PMPMd PMPM PM{PM {PMQMH QM-QMh-QM;QMD;QMwQMwQM+QM+QM)QM)QM/RML/RMRMRMASMASMSMSMTMTMSUMSUM)fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U;{ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U;{ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U;{  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7M7operation.4exchange :z2breasonOperatorInputsvalue8invocations1 R(  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r0_p64_c0_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements1800input0Elements1800invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1<R$vHl>"t  L  ^ B bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  JJ)0*044>?IISS]g^ghhr*s*} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%mmS S""$9%9'')*,,./1x1x335^6^88:D;D==?(@(BBD E G{G{IIK]L]NNP?Q?SSU!V!XXZ[]t]t__aVbVddf8g8iiklnnpprmsmuuwOxOzz|1}1ֆֈFF&&  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMOEPMOEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMgOMTgOMOMOM'OM'OM'PM('PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PMQPM QPMQM0 QM-QMP-QME9QM,E9QMQMQMwRM$wRMORMORMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 -m=}  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 -m=}  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 -m=}   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 =]Hh b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1$d bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1f1|G  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>$?$IIS T ^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hbbd0e0ggijllnoqtqtssu\v\xxzD{D}},,tt^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMi9QM,i9QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zI b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 d. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zI b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 d. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zI  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 d.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1J bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1HrG  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMaOMTaOMOMOM!OM!OM!PM(!PMDPMDPM3LPM3LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM;QM,;QMIQMIQMkRM$kRMCRMCRM}SM}SM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ,l<| bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ,l<| bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ,l<|  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 :l b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1  ] ( s _ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>!?!IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikflfnnpJqJssu.v.xxz{}}hhڄچNN44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSMwTMwTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 e0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 e0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 e0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ff b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 q F  /o } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMOMTOMOMOMKOMKOM-PM(-PMDPMDPM]LPM]LPMUPM(UPMYPMYPMmPMmPMPMPM/PM /PMPM PMPML PM1PM 1PMcPM cPMQM0 QM-QMP-QM?9QM,?9QMݎQMݎQMRM$RM[RM[RMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IS@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IS@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IS@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6VRr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1_ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1m:T / } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM]9QM,]9QMUQMUQMRM$RMmRMmRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 d" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 d" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 d"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations19y bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1+~Q$ i } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$o%o'')_*_,,.O/O113?4?668/9/;;=>@@BCEEGGIwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMOMTOMOMOMEOMEOM'PM('PMDPMDPMWLPMWLPMUPM(UPMYPMYPMmPMmPMPMPM)PM )PMPM PMPML PM+PM +PMcPM cPMQM0 QM-QMP-QM;QM,;QMmQMmQMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JR> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JR> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JR>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 =]Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 ! n ;  | } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM;QM,;QMQMQM}RM$}RMURMURMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 e$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 e$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 e$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 w J  p < } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)=*=44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QMK9QM,K9QM7QM7QMRM$RMaRMaRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 "b;{  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 "b;{  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 "b;{   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$DKk b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1"b bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1[. B } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  ZZ)F*F44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln>o>qqs&t&vvxy{{}}jjނބRRƇƉ::"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QMQ9QM,Q9QM+QM+QMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d3  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1(h bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1_0 8x } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  UU)C*C44>1?1IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd`e`ggiJjJlln4o4qqstvvxy{}{}}}gg܂܄QQƇƉ;;%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QM;QM,;QMǏQMǏQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 !a;{  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 !a;{  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 !a;{   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bb8X b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 T ' z M  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)>*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z9z="=zA"AzE*reasonOperatorKernelvalue10kernelSpecoutputElements576input0Elements640input1Elements62722Planned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })binvocations1lOM͚OM͚OMkOMLkOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 L bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 L bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 : b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 R # t E   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)<*<44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMaOMTaOMOMOM!OM!OM3PM(3PMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QMc9QM,c9QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @<|  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @<|  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @<|   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 q2 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations18x bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`> z H } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOM[OMT[OMOMOMOMOMPM(PM1EPM1EPM-LPM-LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM]9QM,]9QMQMQMRM$RMgRMgRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y(  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,LXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations10p bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@lB  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99 yy b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMaOMaOMOMLOMaOMTaOMOMOM!OM!OM3PM(3PMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf#?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbdegsgsiikWlWnnp;q;ssuvxxz{}u}uYY˄ˆ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMgOMTgOMOMOM'OM'OM9PM(9PMDPMDPM9LPM9LPMUPM(UPMXPMXPM nPM nPMPMPM PM  PMPM PMPML PM PM  PMPM PMWQM0 WQM-QMP-QM{9QM,{9QMɐQMɐQMRM$RMaRMaRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W;{ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W;{ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W;{  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18! s  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OMaOMTaOMOMOM!OM!OMPM(PM+EPM+EPM3LPM3LPMUPM(UPMXPMXPM_nPM_nPMPMPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QMu9QM,u9QMcQMcQMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {:Qq b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1F bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1yZ ; f } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  ]])O*O44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk]] O O  AA33%%  " # %%'')t*t,,.f/f113X4X668J9J;;=<><@@B.C.EEG H JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMgOMTgOMOMOM'OM'OM9PM(9PMDPMDPM9LPM9LPMUPM(UPMXPMXPM nPM nPMPMPM PM  PMPM PMPML PM PM  PM!PM !PM]QM0 ]QM-QMP-QM'%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OMaOMTaOMOMOM!OM!OMPM(PM1EPM1EPM3LPM3LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM3?3IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!uuWW b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOMeOMOM$OMPMPM1EPM1EPMiIPM$iIPMenPMenPMPMPM;PM$;PMPMPM PM PM1QM 1QMQM| QMRM RMRM RMSM SMׂTM ׂTMTUMTUMOgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19mS! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19mS! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19mS! b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>A?AIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIiJiLLNWOWQQSETEVVX3Y3[[]!^!``bceeggitjtlln]o]qqsAtAvvx%y%{{} ~ {{__чщCC'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOM[OM[OMPMPM+EPM+EPM-LPM-LPM_nPMp_nPMPMPMPMPMoPM`oPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Gg  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)T*T44>B?BIIS.T.^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44$$  "#%|%|'')l*l,,.\/\113L4L668<9<;;=,>,@@BCEEG H JJLLNnOnQQSZTZVVXFYF[[]2^2``bceeg h jjllnlolqqsXtXvvxDyD{{}0~0~~jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOMeOMOM$OMPMPM7EPM7EPMiIPM$iIPMknPMknPM PM PM;PM$;PMPMPM PM PM1QM 1QMQM| QMRM RMmRM mRMSM SM}TM }TMMTUMMTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:nQ$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:nQ$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:nQ$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  __)I*I44>3?3IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uu__ I I  33||f f""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUtVtXXZ^[^]]_H`Hbbd2e2ggijllnoququssuYvYxxz={=}}!!ww[[͎͐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOM[OM[OMPMPM+EPM+EPM-LPM-LPM_nPMp_nPMPMPMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Pp  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)L*L44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$^%^'')J*J,,.6/6113"4"6689;;==?p@pBBD\E\GGIFJFLLN.O.QQSTVVXXZr[r]]_Z`ZbbdBeBggi*j*llnoqqssunvnxxzV{V}}>>&&jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMKPMKPMDPMDPM{IPM{IPMnPMpnPMPMPMMPMMPMPM`PM PM PM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1W} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1W} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1W  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  kk)W*W44>A?AIIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG;;//  "###%%'(**,,.q/q113]4]668I9I;;=5>5@@B!C!EEG H JJLLNiOiQQSQTQVVX9Y9[[]!^!``b c e}e}ggiejellnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMcPM`cPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1@`  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>8?8IIS"T"^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGI`J`LLNJOJQQS4T4VVXY[[]^`}`}bbdgegggiQjQlln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMyOMyOMOM OMOMOMKPMKPMDPMDPM{IPM{IPMnPMpnPMPMPMMPMMPMPM`PM PM PM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1V} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1V} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1V  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)M*M44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%y%y'')a*a,,.I/I1131416689;;=>@u@uBBD]E]GGICJCLLN'O'QQS T V}V}XXZa[a]]_E`Ebbd)e)ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMuPM`uPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Qq  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])G*G44>/?/IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd$e$ggi j l}l}nnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMsOMsOMOM OMOMOMEPMEPMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PM]PM`]PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1=]  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>+?+IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?W@WBBD=E=GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikmlmnnpSqSssu9v9xxz{}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOM[OM[OMPMPM1EPM1EPM-LPM-LPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 } bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1   bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)L*L44>4?4IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@00  "#%~%~'')j*j,,.V/V113B4B668.9.;;=>@@BCEtEtGGI\J\LLNDODQQS,T,VVXY[[]]_p`pbbdXeXggi@j@lln(o(qqstvvxxzl{l}}TTȂȄ<<!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMsOMsOMOM OMOMOM?PM?PMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMcPM`cPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMTMT TMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Dd  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  YY)?*?44>!?!IIST^t^thhrTsT} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    ||b b""$H%H'').*.,,./11335m6m88:S;S==?5@5BBDEGGIIKjLjNNPLQLSSU.V.XXZ[]]__acbcddfEgEiik'l'nnp q szszuuw\x\zz|>}> ppPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOM[OM[OMPMPM1EPM1EPM-LPM-LPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)D*D44>(?(IIS T ^~^~hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00 x x""$`%`'')H*H,,.0/011346689;t;t==?X@XBBD[>]]_"`"bbdegxgxiik\l\nnp@q@ssu$v$xxz{}z}z^^ЄІ@@"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMmOMmOM OM  OMOMOM?PM?PMDPMDPMIPMIPMnPMpnPMPMPM_PM_PM]PM`]PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1.n} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1.n} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1.n  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Bb  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  \\)F*F44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// { {""$e%e'')O*O,,.9/9113#4#668 9 ;;==?l@lBBDVEVGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77}}gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1], b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1], b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1], b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ^^)P*P44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll^^ P P  BB44&&  " # %%'')u*u,,.g/g113Y4Y668K9K;;==>=@@B/C/EEG!H!JJLMOOQQStTtVVXbYb[[]P^P``b*?*IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUȉȋ;;!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ZZ)H*H44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llZZ H H  66$$ w w""$e%e'')S*S,,.A/A113/4/6689;;= > @@BBDpEpGGI\J\LLNFOFQQS0T0VVXY[[]^`y`ybbd_e_ggiEjElln)o)qqs t v|v|xxz^{^}}@@""ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PMQPM`QPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1;[  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOMOOMOOMPMPM=EPM=EPM!LPM!LPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f5 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMoPM`oPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  SS)=*=44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiSS = =  ''ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?K@KBBD5E5GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMKPM`KPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1+k} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1+k} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1+k  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations16V  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPMIPMIPMmPMpmPMPMPMSPMSPMiPM`iPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1,l} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1,l} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1,l  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ww  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM[OM[OMOM OMOMOM'PM'PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SM;TMT ;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>?IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMCOMCOMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMPMPMPM`PM?QM?QM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM9eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xG b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>(?(IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;= > @@BBDhEhGGIPJPLLN8O8QQS T VVXY[|[|]]_d`dbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMYRM YRM1RMp 1RMkSMt kSMہTMT ہTMSUMSUMSfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMCOMCOMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMPMPM'PM`'PMcQMcQM1QM1QMQML QMkRM kRMRMp RMqSMt qSM#TMT #TMRUMRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1=9  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?L@LBBD0E0GGIJLLNNPjQjSSUNVNXXZ2[2]]_`bbdegtgtiikXlXnnpr b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1(h} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1(h} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1(h  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1'K  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  PP)<*<44>%?%IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  RR)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``RR D D  66((   ""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOOMOOMOM OMOMOM!PM!PMDPMDPMuIPMuIPMmPMpmPMPMPMGPMGPM]PM`]PMQMQM1QM1QMQMT QMqRM qRMRMx RMwSM| wSMGTM\ GTM=RUM=RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1)i} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1)i} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1<p b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1)i  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1Lp  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL):*:44>"?"IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMRMp RMSMt SM}TMT }TMsRUMsRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)D*D44>0?0IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1 OM%OM%OMOM|OM'OM'OM]OM]OMOM|OMOMHOMPMPMDPMPDPMIPMXIPM/MPM/MPMVPMPVPMYPMYPMmPMmPMgPM$ gPM˳PM, ˳PMPM PMPM$ PMPM PMPM| PM3PMX3PMoQMoQM-QM-QM;QM;QMpQM\pQMQMQMQMQMRM8RMmRMmRMSMSM!SM!SMTMlTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pq b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pq b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Pq  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations15uBH  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d5B F_4J NT\ d (  l  0 r  4 x  < bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10@@  RR)N*N44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1@@22 $ $  66((   ""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')u*u,,.a/a113M4M668999;;=>@{@{BBDgEgGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWllnKoKqqs3t3vvxy{{}~ww__ӇӉGG//  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OM%OM%OMOM|OM'OM'OM]OM]OMOM|OMOMHOMPMPMDPMPDPMIPMXIPM/MPM/MPMVPMPVPMYPMYPMmPMmPMaPM$ aPM˳PM, ˳PMPM PMPM$ PMPM PMPM| PMKPMXKPMQMQM-QM-QM  /Z F7 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10??  NN)D*D44>2?2IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1??--    **}}k k""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln3o3qqstvvxxzh{h}}JJ,,bb# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM7OMl7OMOMOMOMOMPM@PM[EPM[EPM LPM LPMUPM@UPMXPM XPMnPMnPM-PM-PM۵PM ۵PMePM ePMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM;QMD;QMpQMpQMgQMgQMeQM eQMqRMqRMIRMpIRMSMtSMSMTSMGTMGTMTUM$TUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 B bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 B bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 B  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <\1Q b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1=}7w  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d=z7t1)n+_h%:b\  V   P  M   G   bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)?*?44>'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')S*S,,.;/;113#4#668 9 ;;==?F@FBBD.E.GGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II--  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOOMOOMOMdOMIOMlIOMOMOM OM OM!PM@!PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PM3PM 3PMoQMH oQM-QMh-QM;QMD;QMpQMpQMQMQMQM QMRMRMgRMpgRMSMtSMSMTSMTMTMTUM$TUMmgUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 4t=} bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 4t=} bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 4t=}  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1.n=}7w  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d.=z7\t31n+h%b\  V   P  M   G   bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  PP)@*@44>?IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``PP @ @  00   x x""$h%h'')X*X,,.H/H113848668(9(;;=>@@BCEEGGIPJPLLN?IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbd e g}g}iikclcnnpIqIssu/v/xxzz|h}hہNNTTƉƋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOOMOOMOMdOMCOMlCOMOMOMOMOM!PM@!PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMqPM qPMPMd PMPM PMWPM WPMQMH QM-QMh-QM;QMD;QMpQMpQMQMQMQM QMwRMwRMORMpORMSMtSMSMTSM}TM}TMMTUM$MTUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 3s=} bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 3s=} bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1=q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 3s=}  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1=}7w  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d=z7t1 na+8h%b\  V   P  M   G  5u bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  LL)8*844>?IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$J%J'')6*6,,."/"11346688:p;p==?\@\BBDHEHGGIJLLNNPoQoSSUxVxXXZ`[`]]_H`Hbbd0e0ggijllnoq|q|ssudvdxxzL{L}}44xx``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMUEPMUEPMLPMLPMUPM@UPMXPM XPMnPMnPM'PM'PMPM PMwPM wPMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QMW8x  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[u:P)xU2  l  I  &   ` ?{X bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|}hhjjڋڍJJ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMUOMTUOMOMOMOMOM'PM('PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QMA4QM,A4QMQMQM}RM$}RMURMURMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T=} bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T=} bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T=}  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 3S b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1%e bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1%~W0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)<*<44>*?*IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$Y%Y'')G*G,,.5/5113#4#6689;;==?v@vBBDdEdGGIRJRLLN'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMUOMUOMOMLOMUOMTUOMOMOMOMOM!PM(!PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QM7QM7QMkRM$kRMCRMCRM}SM}SMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U=} bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U=} bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U=}  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Xx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 b;N } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)7*744>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz``ӉӋFF,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OM[OMT[OMOMOMOMOMPM(PMOEPMOEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QMQMQMkRM$kRMCRMCRM}SM}SM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 X bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 X bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 X  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 9Y b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1^5 2r } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>"?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMgOMTgOMOMOM'OM'OM-PM(-PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PMEPM EPMQM0 QM-QMP-QM;4QM,;4QMQMQM}RM$}RMURMURMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 )i?  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 )i?  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 )i?   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2R3S b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1\ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1wR-  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;=>@@BBDjEjGGIRJRLLN:O:QQS"T"VVX Y [~[~]]_f`fbbdNeNggi6j6llnoqqstvzvzxxzb{b}}JJ22rr b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMsOMTsOMOMOM3OM3OMPM(PMCEPMCEPMELPMELPMUPM(UPMYPMYPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM;4QM,;4QMYQMYQMRM$RM[RM[RMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 b. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 b. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xE  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 b.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 \| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1^ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1sHn  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMgOMTgOMOMOM'OM'OM'PM('PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM6QM,6QMUQMUQMeRM$eRM=RM=RMwSMwSM#TM#TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 (h>~ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 (h>~ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 (h>~  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 /^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1c>g } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^t^thhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbddfngniikRlRnnp6q6ssuvxxzz|p}pTTƄƆ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMyOMTyOMOMOM9OM9OMPM(PMIEPMIEPMKLPMKLPMUPM(UPM YPM YPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 c0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 c0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 c0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 +K b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rGqC } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  MM)7*744>#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMOMTOMOMOMKOMKOM-PM(-PMDPMDPM]LPM]LPMUPM(UPMYPMYPMmPMmPMPMPM/PM /PMPM PMPML PM1PM 1PMcPM cPMQM0 QM-QMP-QM54QM,54QMюQMюQMRM$RMgRMgRMSMSMTMTMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IU@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IU@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IU@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ?Qq b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1S bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pM* # } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)H*H44>:?:IIS&T&^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%{%{'')m*m,,._/_113Q4Q668C9C;;=5>5@@B'C'EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m o}o}qqsctcvvxIyI{{}/~/mmߌߎQQÑÓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PM=EPM=EPM?LPM?LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QM54QM,54QM/QM/QMRM$RMaRMaRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 b" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 b" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 b"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ff b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Q bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d7 A  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  ]])I*I44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii]] Q Q  EE99--!!  "#%%'(*w*w,,.c/c113O4O668;9;;;='>'@@BCEEGGIuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMOMTOMOMOMKOMKOM-PM(-PMDPMDPM]LPM]LPMUPM(UPMYPMYPMmPMmPMPMPM/PM /PMPM PMPML PM1PM 1PM]PM ]PMQM0 QM-QMP-QM6QM,6QMmQMmQM}RM$}RMURMURMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JT> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JT> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JT>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2RPp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1dA } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM6QM,6QMŎQMŎQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 c$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 c$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n<  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 c$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {9 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]0V  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMUOMTUOMOMOMOMOM3PM(3PMDPMDPM'LPM'LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ^=}  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ^=}  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ^=}   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r )Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 J bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 iH' : } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)D*D44>4?4IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln^o^qqsJtJvvx6y6{{}"~"pp\\ґғ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMǚOMǚOMeOMLeOMUOMTUOMOMOMOMOMPM(PM7EPM7EPM'LPM'LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM)4QM,)4QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1U&w T  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?O@OBBD5E5GGIJLLNOQtQtSSUZVZXXZ@[@]]_&`&bbd e ggiikelennpKqKssu1v1xxz{}}ppVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOM[OMT[OMOMOMOMOM3PM(3PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]=}  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]=}  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]=}   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Cc>^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1eD# } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOMUOMTUOMOMOMOMOMPM(PM7EPM7EPM'LPM'LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QM6QM,6QMQMQMeRM$eRM=RM=RMwSMwSMTMTMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p'?_ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Hj;  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  OO)5*544>?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMaOMTaOMOMOM!OM!OM9PM(9PMDPMDPM3LPM3LPMUPM(UPMXPMXPM nPM nPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @>~  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @>~  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @>~   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 eGg b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1B bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1cD%Z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OM[OMT[OMOMOMOMOMPM(PM1EPM1EPM-LPM-LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM)4QM,)4QMeQMeQMRM$RMaRMaRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 N  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 N  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W$  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 N   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 :[{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X0p  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  VV)@*@44>+?+IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99)) u u""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33{{ee b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMgOMgOMOMLOMaOMTaOMOMOM!OM!OM9PM(9PMDPMDPM3LPM3LPMUPM(UPMXPMXPM nPM nPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @>~ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @>~ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @>~  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~Bb,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1gH) } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOM[OMT[OMOMOMOMOMPM(PM1EPM1EPM-LPM-LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 `Zz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`8hH } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>&?&IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMYOMLYOMgOMTgOMOMOM'OM'OMPM(PM+EPM+EPM9LPM9LPMUPM(UPMXPMXPM_nPM_nPMPMPM PM  PMPM PMPML PM PM  PMuPM uPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1cF) ` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMmOMmOM OML OMgOMTgOMOMOM'OM'OM?PM(?PMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QM!QM!QMwRM$wRMORMORMSMSM5TM5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R=} bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R=} bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R=}  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jQ'g } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)<*<44>"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMYOMLYOMaOMTaOMOMOM!OM!OMPM(PM+EPM+EPM3LPM3LPMUPM(UPMXPMXPM_nPM_nPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Yy[{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 oR5 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  QQ);*;44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`M?MIIS9T9^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1yykk ] ]  OOAA33%%  "#%%' ( **,,.t/t113f4f668X9X;;=J>J@@B@?@IIS(T(^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvjj ^ ^  RRFF::..  ""#"%%'(**,,.p/p113\4\668H9H;;=4>4@@B C EEG H JJLLNhOhQQSPTPVVX8Y8[[] ^ ``bce|e|ggidjdllnLoLqqs4t4vvxy{{}~xx``ԇԉHH00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM_OMOM$OMPMPM1EPM1EPMiIPM$iIPMenPMenPMPMPM;PM$;PMPMPMPMPM1QM 1QMQM| QMRM RMyRM yRMSM SMTM TMkTUMkTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16jS b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16jS b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16jS b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS'T'^^h i sysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdjejggiPjPlln4o4qqstvvxxzi{i}}KK--aa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMUOMUOMPMPM%EPM%EPM'LPM'LPMYnPMpYnPMPMPMPMPM{PM`{PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Qq  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  ff)N*N44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvff V V  FF66&&  "#%z%z'')b*b,,.J/J1132426689;;=>@v@vBBD^E^GGIDJDLLN(O(QQS T V~V~XXZb[b]]_F`Fbbd*e*ggijllnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMQPMQPMDPMDPM{IPM{IPM#nPMp#nPMPMPMMPMMPMPM`PM PM PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1S} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1S} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1S  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)U*U44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%}%}'')m*m,,.]/]113M4M668=9=;;=->-@@BCEEG H JJLLNoOoQQS[T[VVXGYG[[]3^3``bceeg h jjllnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMPM`PM PM PM1QM1QMQML QMRM RMaRMp aRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ZZ)D*D44>*?*IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo[[ G G  33  i i""$S%S'')=*=,,.'/'11346688:p;p==?V@VBBD5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$]%]'')I*I,,.5/5113!4!668 9 ;;==?o@oBBD[E[GGIEJELLN-O-QQSTVVXXZq[q]]_Y`YbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMPM`PM PM PM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ZZ)@*@44>"?"IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  }}c c""$I%I'')/*/,,./11335n6n88:T;T==?6@6BBDEGGIIKkLkNNPMQMSSU/V/XXZ[]]__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMKPMKPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS#T#^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbdhehggiRjRlln.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn^^ N N  >>.. z z""$d%d'')N*N,,.8/8113"4"668 9 ;;==?k@kBBDUEUGGI>J>LLN&O&QQSTVVXXZj[j]]_R`Rbbd:e:ggi"j"lln o q~q~ssufvfxxzN{N}}66||ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMEPMEPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)F*F44>.?.IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI2J2LLNOQQSSUqVqXXZW[W]]_=`=bbd#e#ggi j l|l|nnpbqbssuHvHxxz.{.}}mmSSƎƐ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM_OM _OMUOMUOMPMPM1EPM1EPM'LPM'LPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  YY)C*C44>+?+IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  ~~h h""$R%R'')<*<,,.&/&11346688:o;o==?Y@YBBDCECGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggiikplpnnpTqTssu8v8xxz{}}rrVVɉɋ<<"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMsOMsOMOM OMOMOMEPMEPMDPMDPMIPMIPMnPMpnPMPMPMYPMYPMWPM`WPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1*j} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1*j} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1*j  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1;[  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  aa)M*M44>5?5IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqee Y Y  MMAA11  " # %%'')k*k,,.W/W113C4C668/9/;;=>@@BCEuEuGGI]J]LLNEOEQQS-T-VVXY[[]]_q`qbbdYeYggiAjAlln)o)qqstvvxxzm{m}}UUɂɄ==""{{ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  XX)F*F44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjXX F F  44""u u""$c%c'')Q*Q,,.?/?113-4-6689;;= > @@BBDnEnGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMmOMmOM OM  OMOMOM?PM?PMDPMDPMIPMIPMnPMpnPMPMPM_PM_PMcPM`cPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1+k} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1+k} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1+k  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ff  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  [[)C*C44>'?'IIS T ^}^}hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// w w""$_%_'')G*G,,.///11346688:s;s==?W@WBBD;E;GGIJLLNOQuQuSSUYVYXXZ=[=]]_!`!bbdegwgwiik[l[nnp?q?ssu#v#xxz{}y}y]]τφ??!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  TT)>*>44>(?(IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjTT > >  ((qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLN O QQSSUiViXXZS[S]]_=`=bbd'e'ggijllnnpjqjssuNvNxxz2{2}}llމދPPސ44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMWPM`WPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1>^  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  __)Q*Q44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm__ Q Q  CC55''  " # %%'')v*v,,.h/h113Z4Z668L9L;;=>>>@@B0C0EEG"H"JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOMIOMIOMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJtJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ss  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOMIOMIOMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI8J8LLNOQQSTVrVrXXZV[V]]_:`:bbdeggijltltnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMKPM`KPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1'g} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1'g} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1'g  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations19Y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMPMPM3PM`3PMoQMoQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1!A  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>?IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdegzgziik`l`nnpFqFssu,v,xxz{}}kkބކOO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMoPM`oPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1(h} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1(h} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1(h  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Zz  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)?*?44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMPMPMQPM`QPMQMQM1QM1QMQML QMYRM YRM1RMp 1RMkSMt kSMہTMT ہTMSUMSUMSfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1<\  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]i^ihhrIsI} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3eeՋՍEE b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM-PM-PMDPMDPMcIPMcIPMmPMpmPMPMPM5PM5PMEPM`EPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations12R  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM=OM=OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPMPM`PMQQMQQM1QM1QMQML QM}RM }RMRMp RMSMt SMTMT TMRUMRUM'eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vC b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1&"  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>"?"IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI2J2LLNOQQSTVvVvXXZ^[^]]_F`Fbbd8e8ggi j llnoq|q|ssudvdxxzL{L}}44zzdd b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPM]IPM]IPMmPMpmPMPMPM/PM/PMiPM`iPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1[{  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>"?"IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM=OM=OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPM3PM`3PMoQMoQM1QM1QMQML QMqRM qRMRMp RMwSMt wSMATMT ATM7RUM7RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1IE  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMUOMUOMOM OMOMOM'PM'PMDPMDPMuIPMuIPMmPMpmPMPMPMGPMGPM-PM`-PMiQMiQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM9eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1$d} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1$d} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1$d  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1>  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)C*C44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMٚOMٚOMwOM wOMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMWeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  LL)D*D44>2?2IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMUOMUOMOM OMOMOM!PM!PMDPMDPMuIPMuIPMmPMpmPMPMPMGPMGPMQPM`QPMQMQM1QM1QMQMT QMkRM kRMRMx RMqSM| qSM)TM\ )TMRUMRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1%e} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1%e} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1>r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1%e  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1@d  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>?IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMٚOMٚOMwOM wOMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  HH):*:44>$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^HH 2 2  {{eeO O""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1 OM+OM+OMOM|OM-OM-OMcOMcOMOM|OM#OMH#OMPMPMDPMPDPMIPMXIPM5MPM5MPMVPMPVPMYPMYPMmPMmPMgPM$ gPMѳPM, ѳPMPM PMPM$ PMPM PM PM|  PMiPMXiPMQMQM-QM-QM+?+IIST^^his}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1==--    //  k k""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`ObbdCeCggi+j+llnoqqssuovoxxzW{W}}??''qq# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM7OMl7OMOMOMOMOMPM@PM[EPM[EPM LPM LPMUPM@UPMXPM XPMnPMnPM-PM-PM۵PM ۵PMePM ePMPMd PMPM PMuPM uPMQMH QM-QMh-QM;QMD;QMpQMpQMߏQMߏQMݚQM ݚQMRMRM[RMp[RMSMtSMSMTSMTMTMTUM$TUM7gUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 'Gp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1?=}m  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d?~=|;z9x7v5\t7 3   r  1 p / o  - m  ? bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)@*@44>.?.IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;==?X@XBBDFEFGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln=o=qqs't'vvxy{{}}ppZZχωDD..  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OM%OM%OMOM|OM-OM-OMcOMcOMOM|OM#OMH#OMPMPMDPMPDPMIPMXIPM5MPM5MPMVPMPVPMYPMYPMmPMmPMgPM$ gPMѳPM, ѳPMPM PMPM$ PMPM PM PM|  PM'PMX'PMcQMcQM-QM-QM&?&IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1<<((    ##ooY Y""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD%?%IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$N%N'')8*8,,."/"113 4 6688:k;k==?2@2BBDEGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpeqessuKvKxxz1{1}}ppVVɎɐ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMUOMUOMOMdOMIOMlIOMOMOM OM OM'PM@'PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PMiPM iPMQMH QM-QMh-QM;QMD;QMpQMpQMQMQMQM QM}RM}RMURMpURMSMtSM SMT SMTMTM}TUM$}TUM%gUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 0p? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 0p? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 0p?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1DNZ  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dDLT\ fd,;r 8 ~ i D   P   X  $d  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  MM);*;44> ? IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGI1J1LLNOQQS T VVXY[[] ^ ``bbdpepggi^j^llnQoQqqs5t5vvxy{{}}ooSSŇʼn77  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMUEPMUEPMLPMLPMUPM@UPMXPM XPMnPMnPM'PM'PMPM PMwPM wPMPMd PMPM PM3PM 3PMoQMH oQM-QMh-QM,?,IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN>HIS T ^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__II 3 3  ||ffP P""$:%:'')$*$,,./11335m6m88:W;W==?A@ABBD+E+GGIIKiLiNNPSQSSSU`V`XXZJ[J]]_4`4bbdeggijl}l}nnpiqissuMvMxxz1{1}}kk݉݋OO33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMUEPMUEPMLPMLPMUPM@UPMXPM XPMnPMnPM'PM'PMPM PMwPM wPMPMd PMPM PMWPM WPMQMH QM-QMh-QM'?IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbdegrgriikVlVnnp:q:ssuvxxzz|Q}QÁ55<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMo9QM,o9QM͏QM͏QM}RM$}RMURMURMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1U bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1kD v % } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  WW)C*C44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33''  "#%%'')q*q,,.]/]113I4I668595;;=!>!@@B C EEGGIoJoLLNWOWQQS?T?VVX'Y'[[]^``bbdkekggiSjSlln;o;qqs#t#vvx y {{}}ggۂۄOOÇÉ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OM[OMT[OMOMOMOMOMPM(PMIEPMIEPM-LPM-LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM9QM,9QM!QM!QMRM$RMaRMaRMSMSMTMTMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 3S b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1g bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rO , 7w } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM'PM('PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM #?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$g%g'')O*O,,.7/711346689;{;{==?c@cBBDKEKGGI3J3LLNOQQSSUmVmXXZQ[Q]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OM[OMT[OMOMOMOMOMPM(PMOEPMOEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM!.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMgOMTgOMOMOM'OM'OM-PM(-PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QMo9QM,o9QMQMQMkRM$kRMCRMCRM}SM}SM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 %eA  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 %eA  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 %eA   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 'G^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rM(  @ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  KK)5*544>?IIST^v^vhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?I@IBBD/E/GGIJLLNNPnQnSSUTVTXXZ:[:]]_ ` bbdegygyiik_l_nnpEqEssu+v+xxz{}}jj݄݆PP‰‹44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMsOMTsOMOMOM3OM3OMPM(PMCEPMCEPMELPMELPMUPM(UPMYPMYPMwnPMwnPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM9QM,9QM?QM?QMRM$RMmRMmRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 `. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 `. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 `.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 5U b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1b bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1{Z 9 R } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMgOMTgOMOMOM'OM'OM-PM(-PMDPMDPM9LPM9LPMUPM(UPMXPMXPMmPMmPMPMPM PM  PMPM PMPML PM PM  PM9PM 9PMuQM0 uQM-QMP-QM ?IISS]h^hhhrJsJ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__aWbWddf9g9iiklnnpprnsnuuwPxPzz|2}2ff֋֍FF b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMyOMTyOMOMOM9OM9OMPM(PMIEPMIEPMKLPMKLPMUPM(UPM YPM YPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM!(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMOMTOMOMOMKOMKOM3PM(3PMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PMiPM iPMQM0 QM-QMP-QMo9QM,o9QM QM QM}RM$}RMURMURMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IW@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IW@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IW@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 FfXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1K bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1yV3  [ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  PP):*:44>%?%IIS T ^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--uu__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOMmOMTmOMOMOM-OM-OMPM(PM=EPM=EPM?LPM?LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM9QM,9QM]QM]QMRM$RMaRMaRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 `" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 `" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 `"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 'G b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1] bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1#e F m } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMOMTOMOMOMKOMKOM3PM(3PMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PM?PM ?PM{QM0 {QM-QMP-QM bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JV> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JV>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 'G/O b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1(  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1m J '   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>"?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM!  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 '  i J N } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOM[OMT[OMOMOMOMOM9PM(9PMDPMDPM-LPM-LPMUPM(UPMXPMXPM nPM nPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMo9QM,o9QM-QM-QMRM$RMaRMaRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Z?  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Z?  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Z?   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Mm>^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1F bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1_>  6v } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>/?/IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnKoKqqs/t/vvxy{{}}iiۂۄMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMǚOMǚOMeOMLeOMUOMTUOMOMOMOMOMPM(PM7EPM7EPM'LPM'LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM{9QM,{9QMWQMWQMRM$RMaRMaRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a-  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {5a b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1T bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1{\ = d } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)F*F44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::**  "#%x%x'')d*d,,.P/P113<4<668(9(;;=>@@BBDpEpGGIXJXLLN@O@QQS(T(VVXY[[]]_l`lbbdTeTggi#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMmOMmOM OML OMaOMTaOMOMOM!OM!OM?PM(?PMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QMo9QM,o9QMQQMQQMRM$RMgRMgRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @@  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @@  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @@   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Hh$D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1C bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 kM / [ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM_OML_OMaOMTaOMOMOM!OM!OMPM(PM1EPM1EPM3LPM3LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QMo9QM,o9QM-QM-QMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 L  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 L  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V"  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 L   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p#^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1C bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1}\;  3s } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOM[OMT[OMOMOMOMOMPM(PM1EPM1EPM-LPM-LPMUPM(UPMXPMXPMenPMenPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM2?2IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln'o'qqs t vzvzxxz\{\}}>> ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMsOMsOMOMLOMgOMTgOMOMOM'OM'OMEPM(EPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PM'PM 'PMcQM0 cQM-QMP-QM9QM,9QMɐQMɐQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 } * b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18! s  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMYOMLYOMgOMTgOMOMOM'OM'OMPM(PM+EPM+EPM9LPM9LPMUPM(UPMXPMXPM_nPM_nPMPMPM PM  PMPM PMPML PM PM  PM{PM {PMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 eWw b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18 g  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$r%r'')b*b,,.R/R113B4B668292;;=">"@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM_OML_OMgOMTgOMOMOM'OM'OMPM(PM+EPM+EPM9LPM9LPMUPM(UPMXPMXPM_nPM_nPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM-QMP-QM!,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88%%  ""$n%n'')X*X,,.B/B113,4,6689;;=>@u@uBBD_E_GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((pp b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOOMOOMPMPM%EPM%EPM!LPM!LPMYnPMpYnPMPMPMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ii  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>;?;IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIcJcLLNMOMQQS7T7VVX!Y![[] ^ ``bbdjejggiTjTlln>o>qqs(t(vvxy{{}}qq[[ЇЉEE// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM_OMOM$OMPMPM+EPM+EPMoIPM$oIPM_nPM_nPMPMPMAPM$APMPMPMPMPM1QM 1QMQM| QMRM RMmRM mRMSM SMeTM eTM5TUM5TUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations12fU b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations12fU b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations12fU b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  aa)K*K44>3?3IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd"e"ggijlxlxnnp\q\ssu@v@xxz${$}}zz^^щыDD** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMOOMOOMPMPM%EPM%EPM!LPM!LPMYnPMpYnPMPMPMPMPM{PM`{PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1?s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Rr  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)J*J44>2?2IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI6J6LLNOQQSTVuVuXXZ[[[]]_A`Abbd'e'ggi j llnnpfqfssuLvLxxz2{2}}qqWWʎʐ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM#OM #OMOMOMWPMWPMDPMDPMuIPMuIPM)nPMp)nPMǮPMǮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1O} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1O} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1O  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>?>IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttbb P P  >>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIfJfLLNTOTQQSBTBVVX0Y0[[]^``b c eeggiqjqllnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)O*O44>7?7IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC33  " # %%'')m*m,,.Y/Y113E4E668191;;=>@@BCEwEwGGI_J_LLNGOGQQS/T/VVXY[[]]_s`sbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM#OM #OMOMOMQPMQPMDPMDPMuIPMuIPM#nPMp#nPMPMPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  \\)F*F44>0?0IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr\\ F F  00yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUqVqXXZ[[[]]_E`Ebbd/e/ggijllnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOM7OM7OMPMPM+EPM+EPM LPM LPM_nPMp_nPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)G*G44>+?+IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33 { {""$c%c'')K*K,,.3/311346689;w;w==?[@[BBD?E?GGI#J#LLNOQyQySSU]V]XXZA[A]]_%`%bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  hh)T*T44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD88,,  " # %%' ( **,,.n/n113Z4Z668F9F;;=2>2@@BCEEG H J~J~LLNfOfQQSNTNVVX6Y6[[]^``bcezezggibjbllnJoJqqs2t2vvxy{{}~vv^^҇҉FF.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMOOMOOMPMPM1EPM1EPM!LPM!LPMenPMpenPMPMPMPMPMPM`PM PM PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  aa)S*S44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ooaa S S  EE77))  " # %%'')x*x,,.j/j113\4\668N9N;;=@>@@@B2C2EEG$H$JJLMOOQRTwTwVVXeYe[[]S^S``b?c?eeg)h)jjlmooqqsltlvvxRyR{{}8~8ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMyOMyOMOM OMOMOMKPMKPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)J*J44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%v%v'')^*^,,.F/F113.4.6689;;==?r@rBBDZEZGGI@J@LLN$O$QQSTVzVzXXZ^[^]]_B`Bbbd&e&ggi j l|l|nnp`q`ssuDvDxxz({(}} ~~bbԉԋFF** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMOOMOOMPMPM1EPM1EPM!LPM!LPMenPMpenPMPMPMPMPMPM`PM PM PM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ]])K*K44>7?7IIST^^hisqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo]] K K  99'' z z""$h%h'')V*V,,.D/D113242668 9 ;;=>@@BBDsEsGGI_J_LLNIOIQQS3T3VVXY[[]^`|`|bbdbebggiHjHlln,o,qqstvvxxza{a}}CC%%wwYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMKPMKPMDPMDPMIPMIPMnPMpnPMPMPMYPMYPMQPM`QPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1&f} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1&f} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1&f  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations12R  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  XX)B*B44>(?(IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?T@TBBD:E:GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikjljnnpPqPssu6v6xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM1EPM1EPMKPMKPMenPMpenPMPMPMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)K*K44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++   ""$s%s'')c*c,,.S/S113C4C668393;;=#>#@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllncocqqsOtOvvx;y;{{}'~'uuaaבד b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMsOMsOMOM OMOMOMEPMEPMDPMDPMIPMIPMnPMpnPMPMPMYPMYPM]PM`]PMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1'g} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1'g} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1'g  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1=]  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  VV)<*<44>?IIST^q^qhhrQsQ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11yy_ _""$E%E'')+*+,,./11335j6j88:P;P==?2@2BBDEGGIIKgLgNNPIQISSU+V+XXZ [ ]~]~__a`b`ddfBgBiik$l$nnpqswswuuwYxYzz|;};mm݋ݍMM b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //}}i i""$U%U'')A*A,,.-/-11346689;{;{==?g@gBBDSESGGI=J=LLN%O%QQS T VVXXZi[i]]_Q`Qbbd9e9ggi!j!lln o q}q}ssuevexxzM{M}}55yyaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOM?PM?PMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMQPM`QPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations17W  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  YY)C*C44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, x x""$b%b'')L*L,,.6/6113 4 668 9 ;;==?i@iBBDSESGGI/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMcPM`cPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Jj  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  UU)?*?44>'?'IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)>*>44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM9PM9PMDPMDPM{IPM{IPM nPMp nPMPMPMMPMMPMQPM`QPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1#c} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1#c} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1#c  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1<\  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMPMPMEPM`EPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1.N  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33qq b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPM{IPM{IPM nPMp nPMPMPMMPMMPMiPM`iPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1$d} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1$d} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1$d  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Uu  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMPMPM]PM`]PMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SM#TMT #TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ii  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>?IIST^u^uhhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMEPM`EPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations15U  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>2?2IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOM7OM7OMPMPMCEPMCEPM LPM LPMwnPMpwnPMPMPM۵PM۵PM!PM`!PM]QM]QM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations13/  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMO}O}QQSkTkVVXYYY[[]G^G``b3c3eeghjjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMaOMaOMOM OMOMOM-PM-PMDPMDPMcIPMcIPMmPMpmPMPMPM5PM5PMoPM`oPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1^~  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)>*>44>$?$IIST^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOM7OM7OMPMPMCEPMCEPM LPM LPMwnPMpwnPMPMPM۵PM۵PMEPM`EPMQMQM1QM1QMQML QM}RM }RMRMp RMSMt SM}TMT }TMsRUMsRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uC b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1VR  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdVeVggi?IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdeggiiklllnnpRqRssu8v8xxz{}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMٚOMٚOMwOM wOM OM OMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  OO)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //w w""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM[OM[OMOM OMOMOM'PM'PMDPMDPMoIPMoIPMmPMpmPMPMPMAPMAPMEPM`EPMQMQM1QM1QMQMT QM_RM _RMRMx RMeSM| eSMTM\ TMQUMQUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1!a} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1!a} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1@t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1!a  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations12V  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)4*444>?IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMٚOMٚOMwOM wOM OM OMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM'eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  KK)?*?44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##qq] ]""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1 OM+OM+OMOM|OM-OM-OMcOMcOMOM|OM#OMH#OMPMPMDPMPDPMIPMXIPM5MPM5MPMVPMPVPMYPMYPMmPMmPMmPM$ mPMѳPM, ѳPMPM PMPM$ PMPM PM PM|  PMKPMXKPMQMQM-QM-QM?1?1IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1==11 % %  ==11!!   ""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdaeaggiIjIlln1o1qqstvvxy{u{u}}]]тфEE,,# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM=OMl=OMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMkPM kPMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QM ? IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss] ]""$G%G'')1*1,,./1l1l335V6V88:@;@==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbdeggiiknlnnnpTqTssu:v:xxz { }}yy__щыCC''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OM+OM+OMOM|OM-OM-OMcOMcOMOM|OM#OMH#OMPMPMDPMPDPMIPMXIPM5MPM5MPMVPMPVPMYPMYPMmPMmPMgPM$ gPMѳPM, ѳPMPM PMPM$ PMPM PM PM|  PMWPMXWPMQMQM-QM-QM#?#IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1<<,,    11!!  i i""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbd e ggiikclcnnpGqGssu+v+xxz{}}eeׄ׆II++ # b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOM=OMl=OMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMkPM kPMPMd PMPM PM]PM ]PMQMH QM-QMh-QM?IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qqW W""$=%='')#*#,,. / 1W1W335=6=88:#;#==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##uuUUŐŒ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM[OM[OMOMdOMIOMlIOMOMOM OM OM-PM@-PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PMWPM WPMQMH QM-QMh-QM!?IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaSS E E  77))   ""$x%x'')j*j,,.\/\113N4N668@9@;;=2>2@@B$C$EEGHJkJkLLNYOYQQSGTGVVXYYY[[]G^G``b3c3eeghjjlmooqqsjtjvvxPyP{{}6~6ttXXʑʓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMUEPMUEPMLPMLPMUPM@UPMXPM XPMnPMnPM'PM'PMPM PMwPM wPMPMd PMPM PMEPM EPMQMH QM-QMh-QM{&?&IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd4e4ggijllnoqxqxssu`v`xxz${$}} xxbb  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM[OM[OMOMdOMIOMlIOMOMOM OM OM'PM@'PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PMWPM WPMQMH QM-QMh-QM?IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGI.J.LLNOQQSTVVXY[[]]_p`pbbdVeVggi!?!IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikjljnnpNqNssu2v2xxzz|c}cՁGGRRʼnŋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QMG4QM,G4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Vv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1'g bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1']8  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>1?1IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$i%i'')Y*Y,,.I/I113949668)9);;=>@@B C EEGGIqJqLLN]O]QQSITIVVX5Y5[[]!^!``b c eeggiojolln[o[qqsGtGvvx3y3{{}~ mmYYϑϓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMOEPMOEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QMG4QM,G4QMQMQM}RM$}RMURMURMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1+k bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1+eB ; } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnLoLqqs0t0vvxy{{}}jj܂܄NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM[OM[OMOMLOMUOMTUOMOMOMOMOM-PM(-PMDPMDPM'LPM'LPMUPM(UPMXPMXPMmPMmPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QM[QM[QMwRM$wRMORMORMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1nI$r } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)9*944>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$K%K'')7*7,,.#/#11346688:q;q==?]@]BBDIEIGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--qqYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMUEPMUEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM6QM,6QMQMQMkRM$kRMCRMCRM}SM}SMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V"  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 d b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1|Y6 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMgOMTgOMOMOM'OM'OM3PM(3PMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM;4QM,;4QMQMQMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 !aC  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 !aC  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 !aC   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 \| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1sL%  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hhrtst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdZeZggiDjDlln.o.qqstvvxy{w{w}}aaւքKK55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMyOMTyOMOMOM9OM9OMPM(PMIEPMIEPMKLPMKLPMUPM(UPM YPM YPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QMA4QM,A4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ^. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ^. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yG  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ^.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Vv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1"b bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1"`?R } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGItJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMgOMTgOMOMOM'OM'OM3PM(3PMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PM]PM ]PMQM0 QM-QMP-QM6QM,6QM1QM1QMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  `B bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  `B bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  `B  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1~W0 C } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMOMTOMOMOMKOMKOM9PM(9PMDPMDPM]LPM]LPMUPM(UPMYPMYPM nPM nPMPMPM/PM /PMPM PMPML PM1PM 1PMuPM uPMQM0 QM-QMP-QM54QM,54QMqQMqQMRM$RM[RM[RMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IY@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IY@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IY@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ;[b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 M bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 d;}  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)A*A44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$s%s'')_*_,,.K/K113747668#9#;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33ss b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMA4QM,A4QMQMQMwRM$wRMORMORMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ^" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ^" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n<  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ^"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 SsXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Y bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1z[<)i } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMOMTOMOMOMKOMKOM9PM(9PMDPMDPM]LPM]LPMUPM(UPMYPMYPM nPM nPMPMPM/PM /PMPM PMPML PM1PM 1PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQMkRM$kRMCRMCRM}SM}SM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JX> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JX> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JX>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <Nn b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1i@nT } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)9*944>?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQM_RM$_RM7RM7RMqSMqSMTMTMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8XXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1~_@  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf;?;IIS'T'^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeWW I I  ;;--  "#%|%|'')n*n,,.`/`113R4R668D9D;;=6>6@@B(C(EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m o~o~qqsdtdvvxJyJ{{}0~0nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM͚OM͚OMkOMLkOM[OMT[OMOMOMOMOMPM(PM=EPM=EPM-LPM-LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM;4QM,;4QMQMQMRM$RMaRMaRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Jjf b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1qR3 ` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>*?*IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22zzdd b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OM[OMT[OMOMOMOMOM?PM(?PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UA  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UA  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UA   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 AaHh b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T)~S 5 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMӚOMӚOMqOMLqOMUOMTUOMOMOMOMOMPM(PM=EPM=EPM'LPM'LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 F bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 F bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 F  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]}Bb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1uV7 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMsOMsOMOMLOMaOMTaOMOMOM!OM!OMEPM(EPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMyRMyRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @B  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @B  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @B   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 IiBb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`@ P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>5?5IIS!T!^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjslln_o_qqsKtKvvx7y7{{}#~#qq]]ӑӓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMǚOMǚOMeOMLeOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 J  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 J  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 J   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <\a b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1C bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1bA  3 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMsOMsOMOMLOMaOMTaOMOMOM!OM!OM?PM(?PMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @B bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @B bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @B  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Dd/O b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`@  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)=*=44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM͚OM͚OMkOMLkOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,L` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1^= } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>&?&IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnnphqhssuLvLxxz0{0}}jj܉܋NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMyOMyOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMcPM cPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMmRMmRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  KA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  KA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  KA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bb2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1A bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lWB } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM_OML_OMgOMTgOMOMOM'OM'OMPM(PM+EPM+EPM9LPM9LPMUPM(UPMXPMXPM_nPM_nPMPMPM PM  PMPM PMPML PM PM  PM{PM {PMQM0 QM-QMP-QM/4QM,/4QM[QM[QMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .NZz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1gN5` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ``)L*L44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<00$$  "#%%'(*z*z,,.f/f113R4R668>9>;;=*>*@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMyOMyOMOMLOMgOMTgOMOMOM'OM'OMEPM(EPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM6QM,6QMiQMiQMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ee4 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1-nl } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)<*<44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM_OML_OMgOMTgOMOMOM'OM'OMPM(PM1EPM1EPM9LPM9LPMUPM(UPMXPMXPMenPMenPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 L  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 L  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 L   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6a b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jQG } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOMSOMOM$OMPMPM%EPM%EPMoIPM$oIPMYnPMYnPMPMPMAPM$APMPMPMPMPM1QM 1QMQM| QMRM RMRM RMSM SMłTM łTMTUMTUM=gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1-aY b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1-aY b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1-aY b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  jj)V*V44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ::&&  "#%%'')t*t,,.`/`113L4L668898;;=">"@@B C E~E~GGIfJfLLNNONQQS6T6VVXY[[]^`z`zbbdbebggiJjJlln2o2qqstvvxy{v{v}}^^҂҄FF++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMIOMIOMPMPM+EPM+EPMLPMLPM_nPMp_nPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ]])G*G44>-?-IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr^^ J J  66""  l l""$V%V'')@*@,,.*/*11346688:s;s==?Y@YBBD?E?GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz^^ЉЋBB&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOMYOMOM$OMPMPM%EPM%EPMoIPM$oIPMYnPMYnPMPMPMAPM$APMPMPMPMPM1QM 1QMQM| QMRM RMgRM gRMSM SMMTM MTMTUMTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1.bW b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1.bW b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1.bW b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  dd)L*L44>0?0IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88$$   ""$h%h'')P*P,,.8/8113 4 6689;|;|==?`@`BBDDEDGGI(J(LLN O Q~Q~SSUbVbXXZF[F]]_*`*bbdeggiikdldnnpHqHssu,v,xxz{}}ff؄؆HH**  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMIOMIOMPMPM+EPM+EPMLPMLPM_nPMp_nPMPMPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSUMSUM}fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Au b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ]])C*C44>%?%IIST^x^xhhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$  f f""$L%L'')2*2,,./11335q6q88:W;W==?9@9BBDEGGIIKnLnNNPPQPSSU2V2XXZ[]]__agbgddfIgIiik+l+nnp q s~s~uuw`x`zz|B}B$$ttTTĐĒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOM]PM]PMDPMDPMuIPMuIPM/nPMp/nPMͮPMͮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  hh)Z*Z44>J?JIIS6T6^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvhh Z Z  LL>>00""  "#%%'(**,,.q/q113c4c668U9U;;=G>G@@B9C9EEG+H+JJLMOOQRT~T~VVXlYl[[]Z^Z``bFcFeeg0h0jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM7OM7OMPMPM1EPM1EPM LPM LPMenPMpenPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ^^)H*H44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11 } }""$g%g'')Q*Q,,.;/;113%4%6689;;==?n@nBBDXEXGGIAJALLN)O)QQSTVVXXZm[m]]_U`Ubbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM#OM #OMOMOMWPMWPMDPMDPMuIPMuIPM)nPMp)nPMǮPMǮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdgegggiMjMlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OM7OM7OMPMPM1EPM1EPM LPM LPMenPMpenPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  \\)F*F44>.?.IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  k k""$U%U'')?*?,,.)/)11346688:r;r==?\@\BBDFEFGGI.J.LLNOQQSSUmVmXXZS[S]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM#OM #OMOMOMWPMWPMDPMDPMoIPMoIPM)nPMp)nPMǮPMǮPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)R*R44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%z%z'')j*j,,.Z/Z113J4J668:9:;;=*>*@@BCEEG H JJLLNlOlQQSXTXVVXDYD[[]0^0``bceeghj~j~llnjojqqsVtVvvxByB{{}.~.||hhޑޓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMǚOMǚOMeOM eOMIOMIOMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMPM`PM PM PM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S! b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>7?7IIS%T%^^h i s{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI_J_LLNMOMQQS;T;VVX)Y)[[]^``bce|e|ggijjjllnSoSqqs7t7vvxy{{}}qqUULJlj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Z%Z'')F*F,,.2/21134668 9 ;;==?l@lBBDXEXGGIBJBLLN*O*QQSTVVXXZn[n]]_V`Vbbd>e>ggi&j&llnoqqssujvjxxzR{R}}::"" ~~ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMǚOMǚOMeOM eOMIOMIOMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMPM`PM PM PM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  WW)A*A44>+?+IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmWW A A  ++tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O QQSSUlVlXXZV[V]]_@`@bbd*e*ggijllnnpmqmssuQvQxxz5{5}}ooSSŎŐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMKPMKPMDPMDPMIPMIPMnPMpnPMPMPMSPMSPMPM`PM PM PM1QM1QMQML QMRM RMsRMp sRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1"b} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1"b} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1"b  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdeeeggiOjOlln9o9qqs#t#vvx y {{}}llVVˇˉ@@** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMOMOMPMPM7EPM7EPMKPMKPMknPMpknPM PM PMõPMõPMPM`PM PM PM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  aa)M*M44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==11%%  "#%%'(*{*{,,.g/g113S4S668?9?;;=+>+@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMKPMKPMDPMDPMIPMIPMnPMpnPMPMPMYPMYPMPM`PM PM PM1QM1QMQML QMRM RM[RMp [RMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1#c} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1#c} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1#c  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)C*C44>+?+IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$V%V'')@*@,,.*/*11346688:s;s==?]@]BBDGEGGGI/J/LLNOQQSSUnVnXXZT[T]]_:`:bbd e ggijlylynnp_q_ssuEvExxz+{+}}jj݉݋PPÎÐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMõPMõPMPM`PM PM PM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  ]])E*E44>+?+IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==--   ""$q%q'')Y*Y,,.A/A113)4)6689;;==?m@mBBDUEUGGI;J;LLNOQQSTVuVuXXZY[Y]]_=`=bbd!e!ggijlwlwnnp[q[ssu?v?xxz#{#}}yy]]ωϋAA%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMyOMyOMOM OMOMOMEPMEPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMKPM`KPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1.N  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ^^)J*J44>2?2IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>..  "#%|%|'')h*h,,.T/T113@4@668,9,;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOM͚OM͚OMkOM kOM=OM=OMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMQPM`QPMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations14T  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>!?!IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPM]PM`]PMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  XX)@*@44>$?$IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, t t""$\%\'')D*D,,.,/,11346688:p;p==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPM{IPM{IPMnPMpnPMPMPMMPMMPMKPM`KPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1_} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1_} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1_  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations15U  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMQPM`QPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n< b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1;[  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--ss]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM9PM9PMDPMDPM{IPM{IPM nPMp nPMPMPMMPMMPMcPM`cPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 `} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 `} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 `  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ll  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMPMPMoPM`oPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Vv  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPMcIPMcIPM nPMp nPMPMPM5PM5PMKPM`KPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations18X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>4?4IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOM7OM7OMPMPMIEPMIEPM LPM LPM}nPMp}nPMPMPM۵PM۵PM-PM`-PMiQMiQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMQeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wE b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1@<  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLNAOAQQS/T/VVXY[[] ^ ``bbdpepggi^j^llnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMgOMgOMOM OMOMOM3PM3PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMiPM`iPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Yy  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>&?&IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOM1OM1OMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMյPMյPMQPM`QPMQMQM1QM1QMQML QMwRM wRMRMp RM}SMt }SMYTMT YTMORUMORUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wG b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1c_  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>?IIS T ^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQvQvSSU`V`XXZJ[J]]_4`4bbdeggijl}l}nnpiqissuMvMxxz1{1}}kk݉݋OO33 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMPM`PMPMPM1QM1QMQMQMRM@RMRM RMSM SMłTM łTMRUMr RUMceUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1\} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1\} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1\  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-goperation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z 1z5"5z9"9b=reasonOperatorInputsvalue7kernelSpecoutputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7  operation.6exchange :z2  reasonOperatorInputsvalue8Planned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })binvocations10bb  PP)@*@44>,?,IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OM OM OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMłTMT łTMRUMRUMceUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  UU)K*K44>5?5IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11%%  " # %%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM[OM[OMOM OMOMOM-PM-PMDPMDPMoIPMoIPMmPMpmPMPMPMAPMAPMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1]} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1]} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bv b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1]  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM);*;44>#?#IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMߚOMߚOM}OM }OM OM OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SMMTMT MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1 OM1OM1OMOM|OM3OM3OMiOMiOMOM|OM)OMH)OMPMPMDPMPDPMJPMXJPM;MPM;MPMVPMPVPMYPMYPMmPMmPMmPM$ mPM׳PM, ׳PM PM  PMPM$ PMPM PMPM| PM!PMX!PM]QM]QM-QM-QMi$?$IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations177##    !!  wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}ccՉՋGG++# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMqPM qPMPMd PMPM PMWPM WPMQMH QM-QMh-QMo bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)*44>-?-IIS!T!^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$u%u'')a*a,,.M/M11346688:u;u=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbd]e]ggiEjElln-o-qqstvvxxzq{q}}YY͂̈́AA((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OM+OM+OMOM|OM3OM3OMiOMiOMOM|OM)OMH)OMPMPMDPMPDPMJPMXJPM;MPM;MPMVPMPVPMYPMYPMmPMmPMmPM$ mPM׳PM, ׳PM PM  PMPM$ PMPM PMPM| PMQPMXQPMQMQM-QM-QM)=QM)=QMqQM\qQM%QM%QM#QM#QM_RM8_RM7RM7RMqSMqSMSMSMTMlTMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ot b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ot b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ot  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1h:zR  L  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d(<Pdx  2 D ) V  h i z H  D0j<| bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1088  PP)6*644>?IIST^y^yhhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations188$$    ##ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?.@.BBDEGGIIKcLcNNPEQESSU'V'XXZ [ ]z]z__ahbhddfJgJiik,l,nnpqssuuwaxazz|C}C%%wwWWǐǒ# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMCOMlCOMOMOMOMOMPM@PMgEPMgEPMLPMLPMUPM@UPMXPM XPMnPMnPM9PM9PMPM PMqPM qPMPMd PMPM PM!PM !PM]QMH ]QM-QMh-QM b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1w.n#   b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dwne\SJA8-"   \  %  n  v  kR`C8 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)*44>!?!IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$W%W'')?*?,,.'/'1t1t335\6\88:D;D==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆGG))   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMaOMaOMOMdOMIOMlIOMOMOM OM OM-PM@-PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PM'PM 'PMcQMH cQM-QMh-QMK>HIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``PP @ @  00    l l""$V%V'')@*@,,.*/*11346688:s;s==?]@]BBDGEGGGI J LLNNPhQhSSUvVvXXZ^[^]]_F`Fbbd8e8ggi j llnoq|q|ssudvdxxzL{L}}44||ff  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMIOMlIOMOMOM OM OMPM@PM[EPM[EPMLPMLPMUPM@UPMXPM XPMnPMnPM-PM-PMPM PMwPM wPMPMd PMPM PM]PM ]PMQMH QM-QMh-QMQ;?;IIS'T'^^hhrs} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeWW I I  ;;--  "#%|%|'')n*n,,.`/`113R4R668D9D;;=6>6@@B(C(EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m ooqqsftfvvxLyL{{} ~ eeppTTƑƓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM[OM[OMOMdOMIOMlIOMOMOM OM OM-PM@-PMDPMDPMLPMLPMUPM@UPMXPM XPMmPMmPMPMPMPM PMwPM wPMPMd PMPM PMWPM WPMQMH QM-QMh-QME>HIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?K@KBBD5E5GGIIKkLkNNPQQQSSU^V^XXZD[D]]_*`*bbdeggiiklllnnpPqPssu4v4xxz{}}nnTTljNj::   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMaEPMaEPMLPMLPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PMwPM wPMPMd PMPM PM'PM 'PMcQMH cQM-QMh-QM;QMD;QMpQMpQM[QM[QMYQM YQMwRMwRMORMpORMSMtSMSMTSMwTMwTMGTUM$GTUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  @ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1CI   b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dCI OU[a$ g ) * t  m ?  0 s  6 y  <v bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln&o&qqstvyvyxxz4{4}}ssUU  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOM[OMT[OMOMOMOMOM3PM(3PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM{9QM,{9QMQMQM}RM$}RMURMURMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 #C b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1[ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1}X3  K } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)<*<44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$Y%Y'')G*G,,.5/5113#4#6689;;==?v@vBBDdEdGGITJTLLNBOBQQS0T0VVXY[[] ^ ``bbdqeqggi_j_llnHoHqqs,t,vvxy{{}}ff؂؄JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOM[OMT[OMOMOMOMOMPM(PMUEPMUEPM-LPM-LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMQ9QM,Q9QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V"  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations13s bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Nh C } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>5?5IIS!T!^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjslln_o_qqsKtKvvx7y7{{}#~#qq]]ӑӓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMaOMaOMOMLOMUOMTUOMOMOMOMOM3PM(3PMDPMDPM'LPM'LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM ? IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$;%;'')%*%,,./11335n6n88:X;X==?B@BBBD,E,GGIJLLNOQwQwSSUaVaXXZK[K]]_5`5bbdeggi j l~l~nnpbqbssuFvFxxz*{*}}dd։֋HH,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PM[EPM[EPM3LPM3LPMUPM(UPMXPMXPMnPMnPM-PM-PMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM;QM,;QMyQMyQMwRM$wRMORMORMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 %E b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 5  O   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$M%M'')9*9,,.%/%11346688:s;s==?_@_BBDKEKGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMgOMTgOMOMOM'OM'OM9PM(9PMDPMDPM9LPM9LPMUPM(UPMXPMXPM nPM nPMPMPM PM  PMPM PMPML PM PM  PM3PM 3PMoQM0 oQM-QMP-QMo9QM,o9QMǏQMǏQMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]E  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]E  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]E   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~%E b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1J bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`9 k  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  XX)D*D44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44((  "#%%'')r*r,,.^/^113J4J668696;;=">"@@BCEEGGIpJpLLNXOXQQS@T@VVX(Y([[]^``bbdlelggiTjTlln/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOMgOMTgOMOMOM'OM'OM9PM(9PMDPMDPM9LPM9LPMUPM(UPMXPMXPM nPM nPMPMPM PM  PMPM PMPML PM PM  PMoPM oPMQM0 QM-QMP-QM$?$IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpTqTssu8v8xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMUEPMUEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM'PM'PMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM;QM,;QMQMQMqRM$qRMIRMIRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 +K b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 D  b 1  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}cc։֋II// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OMOMTOMOMOMKOMKOM?PM(?PMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PMEPM EPMQM0 QM-QMP-QM]9QM,]9QMQMQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  I[@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  I[@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  I[@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }0P'G b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations19y bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1CqH  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL)6*644>?IIST^w^whhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdegzgziik`l`nnpFqFssu,v,xxz{}}kkބކQQÉË55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMIEPMIEPM?LPM?LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QMQ9QM,Q9QM+QM+QMRM$RMaRMaRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 \" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 \" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 \"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 cf b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1)i bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`1 9y } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)E*E44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii]] Q Q  EE99))  "#%w%w'')c*c,,.O/O113;4;668'9';;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbdSeSggi;j;lln#o#qqs t vvxxzg{g}}OOÂÄ77ww b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OMOMTOMOMOMKOMKOM?PM(?PMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PMuPM uPMQM0 QM-QMP-QM;QM,;QM3QM3QM_RM$_RM7RM7RMqSMqSMTMTMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JZ> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JZ> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JZ>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 d b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 v M $ @ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  LL)2*244>?IISS]i^ihhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ooU U""$;%;'')!*!,,./1z1z335`6`88:F;F==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3gg׋׍GG b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM;QM,;QMQMQMqRM$qRMIRMIRMSMSM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Gg-M b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 S $ u F   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>!?!IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1p!OMsOMsOMOMTOM[OM\[OMOMOMOMOMEPM0EPMDPMDPM-LPM-LPMUPM0UPMXPMXPMnPMnPMPMPMPM PMPM PMPMT PMPM PMPM PMPMH PMPM PM ,QM ,QMW9QMW9QMQMQMRMRM[RMl[RMSMpSMTMPTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 RC  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 RC  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 RC   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes1152patternContiguousinvocations1 bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1z b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1*j bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(V-  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  QQ);*;44>&?&IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqvqvssu^v^xxzF{F}}..vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMӚOMӚOMqOMLqOM[OMT[OMOMOMOMOMPM(PMCEPMCEPM-LPM-LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QMW9QM,W9QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 E bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 E bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 E  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 iXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1.n bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18 b7  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  [[)M*M44>???IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii[[ M M  ??11##  "#%%'')r*r,,.d/d113V4V668H9H;;=:>:@@B,C,EEGHJJLMOOQQSsTsVVXaYa[[]O^O``b;c;eeg%h%jjlmooqqshthvvxNyN{{}4~4rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMsOMsOMOMLOM[OMT[OMOMOMOMOM?PM(?PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 QC  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 QC  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 QC   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 d b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 [ 2 !a } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>#?#IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikhlhnnpLqLssu0v0xxz{}}jj܄܆PPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMٚOMٚOMwOMLwOM[OMT[OMOMOMOMOMPM(PMCEPMCEPM-LPM-LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM;QM,;QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 D bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 D bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 D  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ?d b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 a 6 #c } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  UU)C*C44>1?1IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMyOMyOMOMLOMaOMTaOMOMOM!OM!OMKPM(KPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QMo9QM,o9QMKQMKQMRM$RMgRMgRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @D  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @D  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H|  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @D   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v<Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1bD & P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnLoLqqs0t0vvxy{{}}jj܂܄NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM͚OM͚OMkOMLkOMaOMTaOMOMOM!OM!OMPM(PM7EPM7EPM3LPM3LPMUPM(UPMXPMXPMknPMknPM PM PMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QMu9QM,u9QMQQMQQMRM$RMyRMyRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 H  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 H  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 H   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 dBb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pP 0 T } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)I*I44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllncocqqsOtOvvx;y;{{}'~'uuaaבד b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMyOMyOMOMLOMaOMTaOMOMOM!OM!OMEPM(EPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM͚OM͚OMkOMLkOMaOMTaOMOMOM!OM!OMPM(PM=EPM=EPM3LPM3LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33ww__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 GC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 GC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 GC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 m *Cc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1W bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1YF3 W } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGItJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMǚOMǚOMeOMLeOMgOMTgOMOMOM'OM'OMPM(PM1EPM1EPM9LPM9LPMUPM(UPMXPMXPMenPMenPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]},L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hS> ) Z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>3?3IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbdbebggiLjLlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMyOMyOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMcPM cPMQM0 QM-QMP-QM9(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$l%l'')T*T,,.>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMǚOMǚOMeOMLeOMgOMTgOMOMOM'OM'OMPM(PM7EPM7EPM9LPM9LPMUPM(UPMXPMXPMknPMknPM PM PM PM  PMPM PMPML PM PM  PMPM PMQM0 QM.QMP.QM9*>44>(?(IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI,J,LLNOQQSSUkVkXXZQ[Q]]_7`7bbdeggijlvlvnnp\q\ssuBvBxxz({(}}ggډڋMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOMMOMOM$OMPMPMEPMEPMoIPM$oIPMSnPMSnPMPMPMAPM$APMPMPMPMPM1QM 1QMQM| QMRM RMmRM mRMSM SMkTM kTM;TUM;TUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1)][  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1)][  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1)][  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  aa)K*K44>1?1IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&p p""$Z%Z'')D*D,,../.11346689;w;w==?]@]BBDCECGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~bbԉԋFF** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMIOMIOMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  ff)R*R44>:?:IIS"T"^^h i s|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvjj ^ ^  RRFF66""  "#%%'')p*p,,.\/\113H4H668494;;=>@@BCEzEzGGIbJbLLNJOJQQS2T2VVXY[[]^`v`vbbd^e^ggiFjFlln.o.qqstvvxxzr{r}}ZZ΂΄BB''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOMSOMOM$OMPMPM%EPM%EPMoIPM$oIPMYnPMYnPMPMPMAPM$APMPMPMPMPM1QM 1QMQM| QMRM RM[RM [RMSM SMTM TMSUMSUM}fUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1*^Y  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1*^Y  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1*^Y  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  __)E*E44>'?'IIS T ^z^zhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&h h""$N%N'')4*4,,./11346s6s88:Y;Y==?;@;BBDEGGIIKpLpNNPRQRSSU4V4XXZ[]]__aibiddfKgKiik-l-nnpqssuuwbxbzz|D}D&&vvVVƐƒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMIOMIOMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Cw b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)J*J44>.?.IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvff V V  FF66""  ~ ~""$f%f'')N*N,,.6/611346689;z;z==?^@^BBDBEBGGI&J&LLN O Q|Q|SSU`V`XXZD[D]]_(`(bbd e g~g~iikblbnnpFqFssu*v*xxz{}}ddքֆFF((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM/OM /OMOMOMcPMcPMEPMEPMoIPMoIPM5nPMp5nPMӮPMӮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1G} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1G} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1G  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  bb)L*L44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55""   ""$k%k'')U*U,,.?/?113)4)6689;;==?r@rBBD\E\GGIEJELLN-O-QQSTVVXXZq[q]]_Y`YbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%%mm b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOM eOM7OM7OMPMPM1EPM1EPM LPM LPMenPMpenPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  dd)V*V44>F?FIIS2T2^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrdd V V  HH::,,  "#%%'(*{*{,,.m/m113_4_668Q9Q;;=C>C@@B5C5EEG'H'JJLMOOQRTzTzVVXhYh[[]V^V``bBcBeeg,h,jjlmooqqsotovvxUyU{{};~;!!ww[[͓͑ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM)OM )OMOMOM]PM]PMDPMDPMoIPMoIPM/nPMp/nPMͮPMͮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1F} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1F} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1F  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ^^)H*H44>0?0IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##m m""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI0J0LLNOQQSSUoVoXXZU[U]]_;`;bbdeggijlulunnpYqYssu=v=xxz!{!}}ww[[Ή΋AA'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOM eOM7OM7OMPMPM7EPM7EPM LPM LPMknPMpknPM PM PM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ``)N*N44>:?:IIS"T"^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr`` N N  <<** } }""$k%k'')Y*Y,,.G/G113545668#9#;;=>@@BBDvEvGGIbJbLLNLOLQQS6T6VVX Y [[] ^ ``bbdeeeggiKjKlln/o/qqstvvxxzd{d}}FF(( zz\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOMWPMWPMDPMDPMoIPMoIPM)nPMp)nPMǮPMǮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>;?;IIS)T)^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIcJcLLNQOQQQS?T?VVX-Y-[[]^``b c eegginjnllnWoWqqs;t;vvxy{{}~uuYYˇˉ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOM kOMCOMCOMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U% b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U% b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U% b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ^^)N*N44>>..  ""$v%v'')f*f,,.V/V113F4F668696;;=&>&@@BCEEGHJ|J|LLNhOhQQSTTTVVX@Y@[[],^,``bceeghjzjzllnfofqqsRtRvvx>y>{{}*~*xxddڑړ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM#OM #OMOMOMWPMWPMDPMDPMoIPMoIPM)nPMp)nPMǮPMǮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  YY)C*C44>-?-IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ooYY C C  --vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLNOQQSSUnVnXXZX[X]]_B`Bbbd,e,ggijllnnpoqossuSvSxxz7{7}}qqUUǎǐ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOM kOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ZZ)F*F44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  l l""$X%X'')D*D,,.0/011346689;~;~==?j@jBBDVEVGGI@J@LLN(O(QQSTVVXXZl[l]]_T`Tbbd;?;IIS#T#^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqee Y Y  MMAA55))  "#%%' ( **,,.k/k113W4W668C9C;;=/>/@@BCEEGHJ{J{LLNcOcQQSKTKVVX3Y3[[]^``bcewewggi_j_llnGoGqqs/t/vvxy{{}}ss[[χωCC++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMõPMõPMPM`PM PM PM1QM1QMQML QMRM RMmRMp mRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^. b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  XX)F*F44>2?2IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjXX F F  44""u u""$c%c'')Q*Q,,.?/?113-4-6689;;= > @@BBDnEnGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKlln5o5qqstvvx y {~{~}}hh݂݄RRLJlj<<&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMQPMQPMDPMDPMIPMIPM#nPMp#nPMPMPMSPMSPMPM`PM PM PM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1_} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1_} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1_  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  __)G*G44>-?-IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??//  ""$s%s'')[*[,,.C/C113+4+6689;;==?o@oBBDWEWGGI=J=LLN!O!QQSTVwVwXXZ[[[]]_?`?bbd#e#ggijlylynnp]q]ssuAvAxxz%{%}} {{__щыCC'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMKPMKPMqnPMpqnPMPMPMõPMõPMPM`PM PM PM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  WW)A*A44>)?)IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //}}i i""$T%T'')>*>,,.(/(11346688:q;q==?[@[BBDEEEGGI-J-LLNOQQSSUlVlXXZR[R]]_8`8bbdeggijlwlwnnp]q]ssuCvCxxz){)}}hhۉۋNN44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMKPMKPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPM?PM`?PM{QM{QM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1%E  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  UU)?*?44>%?%IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?Q@QBBD7E7GGIJLLNOQvQvSSU\V\XXZB[B]]_(`(bbdeggiikglgnnpMqMssu3v3xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMӚOMӚOMqOM qOM=OM=OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPM]PM`]PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g7 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)F*F44>.?.IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::**  "#%x%x'')d*d,,.P/P113<4<668(9(;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66tt b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMyOMyOMOM OMOMOMEPMEPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMQPM`QPMQMQM1QM1QMQML QMeRM eRM=RMp =RMwSMt wSMTMT TMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations18X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  SS)9*944>?IISS]n^nhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..vv\ \""$B%B'')(*(,,./11335g6g88:M;M==?/@/BBDEGGIIKdLdNNPFQFSSU(V(XXZ [ ]{]{__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMٚOMٚOMwOM wOM7OM7OMPMPMCEPMCEPM LPM LPMwnPMpwnPMPMPM۵PM۵PMuPM`uPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g9 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)>*>44>"?"IIST^x^xhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**r r""$Z%Z'')B*B,,.*/*11346688:n;n==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMuIPMuIPMnPMpnPMPMPMGPMGPMEPM`EPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1[} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1[} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1[  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1,L  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  VV)@*@44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99)) u u""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMٚOMٚOMwOM wOMOMOMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMPMPM]PM`]PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p@  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Hh  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>:?:IIS&T&^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffXX J J  <<..    "#%}%}'')o*o,,.a/a113S4S668E9E;;=7>7@@B)C)EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m o}o}qqsctcvvxIyI{{}/~/kk݌ݎOO b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOM?PM?PMDPMDPMuIPMuIPMnPMpnPMPMPMGPMGPM]PM`]PMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1\} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1\} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1\  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Cc  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>$?$IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::nnߎߐPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMEPM`EPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations11Q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPM?PM`?PM{QM{QM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yI b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yI b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yI b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1MI  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR)B*B44>0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$j%j'')Z*Z,,.J/J113:4:668*9*;;=>@@B C EEGGIpJpLLN\O\QQSHTHVVX4Y4[[] ^ ``b c eegginjnllndodqqsPtPvvx!?!IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPM]PM`]PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM'eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yK b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1pl  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>$?$IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hbbd0e0ggijllnoq|q|ssudvdxxzL{L}}44xx`` b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMgOMgOMOM OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMłTMT łTMRUMRUMceUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1X} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1X} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1X  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  YY)G*G44>1?1IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUllnIoIqqs1t1vvxy{{}~uu]]чщEE-- b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM˂TMT ˂TMRUMRUMieUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  LL)D*D44>0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln?o?qqs)t)vvxy{{}}rr\\чщFF00 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMaOMaOMOM OMOMOM3PM3PMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SMMTMT MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Y} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Y} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Dx b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Y  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)?*?44>%?%IIS T ^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpaqassuEvExxz){)}} ccՉՋGG++ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMRMp RMSMt SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  KK)=*=44>%?%IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##qq] ]""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpeqessuKvKxxz1{1}}ppVVɎɐ<< b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1 OM1OM1OMOM|OM3OM3OMiOMiOMOM|OM)OMH)OMPMPMDPMPDPMJPMXJPM;MPM;MPMVPMPVPMYPMYPMmPMmPMsPM$ sPM׳PM, ׳PM PM  PMPM$ PMPM PMPM| PMEPMXEPMQMQM-QM-QM;QM;QMpQM\pQM QM QM QM QMRM8RMgRMgRMSMSMSMSMłTMlłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Py b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Py b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Py  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Dd b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1E#c O  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dE# rOAYc(m3x=   G   Q   [  S  %e bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^ LL)D*D44>2?2IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : : wwee{{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKllnAoAqqs+t+vvxy{{}}tt^^ӇӉHH22# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMgEPMgEPMLPMLPMUPM@UPMXPM XPMnPMnPM9PM9PMPM PMwPM wPMPMd PMPM PM!PM !PM]QMH ]QM-QMh-QME'?'IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$[%['')E*E,,.///1|1|335f6f88:P;P==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;##mm  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1 OM1OM1OMOM|OM3OM3OMiOMiOMOM|OM)OMH)OMPMPMDPMPDPMJPMXJPM;MPM;MPMVPMPVPMYPMYPMmPMmPMmPM$ mPM׳PM, ׳PM PM  PMPM$ PMPM PMPM| PM9PMX9PMuQMuQM-QM-QM;QM;QMpQM\pQM QM QM QM QMwRM8wRMORMORMSMSMSMSMYTMlYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ov b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ov b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ov  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z3S9 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1E O  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dE OY_.c}(Lm2w<   F   P   Z  $d bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__ KK)=*=44>'?'IIS T ^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7 pp\\qq] ]""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnpgqgssuMvMxxz3{3}}rrXXˎː>># b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1x OMOMOMOMdOMIOMlIOMOMOM OM OMPM@PMmEPMmEPMLPMLPMUPM@UPMXPM XPMnPMnPM?PM?PMPM PMwPM wPMPMd PMPM PM'PM 'PMcQMH cQM-QMh-QM ~ 0\r\ bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL)*44>$?$IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$I%I'')3*3,,./1i1i335S6S88:=;===?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggijlulunnpYqYssu=v=xxz!{!}}ww]]ЉЋCC))  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMgOMgOMOMdOMOOMlOOMOMOMOMOM3PM@3PMDPMDPM!LPM!LPMUPM@UPMXPM XPMnPMnPMPMPMPM PM}PM }PMPMd PMPM PMKPM KPMQMH QM-QMh-QM{*>44>?IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22""  ""$p%p'')\*\,,.H/H113444668 9 ;;= > @@BBDhEhGGI(J(LLNOQQSSUVXY[|[|]]_d`dbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMaEPMaEPM!LPM!LPMUPM@UPMXPM XPMnPMnPM3PM3PMPM PM}PM }PMPMd PMPM PM'PM 'PMcQMH cQM-QMh-QM' b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1 `P rD  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d Pk 6p@`0R$vH   l  >    `  0T bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>/?/IIST^^hhrusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnMoMqqs1t1vvxy{_{_}}CC''33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMaOMaOMOMdOMOOMlOOMOMOMOMOM3PM@3PMDPMDPM!LPM!LPMUPM@UPMXPM XPMnPMnPMPMPMPM PM}PM }PMPMd PMPM PM!PM !PM]QMH ]QM-QMh-QMu>HIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""j j""$R%R''):*:,,."/"113 4 6~6~88:f;f==?L@LBBD0E0GGIIK]L]NNPAQASSUNVNXXZ2[2]]_`bbdegtgtiikXlXnnp>   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMgEPMgEPM!LPM!LPMUPM@UPMXPM XPMnPMnPM9PM9PMPM PM}PM }PMPMd PMPM PM3PM 3PMoQMH oQM-QMh-QM;QMD;QMpQMpQMQMQMQM QMqRMqRMIRMpIRMSMtSMSMTSMSTMSTM#TUM$#TUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 E  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 E  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 E   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1E O  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dE OYLcd(/m2w<   F   P   Z ^  $d bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>!?!IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpgqgssuKvKxxz{}x}x\\΄ΆiiۉۋMM11  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOM[OMT[OMOMOMOMOM9PM(9PMDPMDPM-LPM-LPMUPM(UPMXPMXPM nPM nPMPMPMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TE bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TE bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TE  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 @` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1S bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1^)t   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  TT)F*F44>8?8IIS$T$^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbTT F F  88**  "#%y%y'')k*k,,.]/]113O4O668A9A;;=3>3@@B%C%EEGHJJLMO~O~QQSlTlVVXZYZ[[]H^H``b4c4eeghjjlmo{o{qqsatavvxGyG{{}-~-kk݌ݎOO b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PM[EPM[EPM3LPM3LPMUPM(UPMXPMXPMnPMnPM-PM-PMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM54QM,54QMՍQMՍQMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  @ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1W bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d1~ '  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMgOMgOMOMLOM[OMT[OMOMOMOMOM9PM(9PMDPMDPM-LPM-LPMUPM(UPMXPMXPM nPM nPMPMPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM6QM,6QM;QM;QMwRM$wRMORMORMSMSMwTMwTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UE bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UE bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fz  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UE  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x= b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1? U N  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbdWeWggi=j=lln!o!qqstvtvtxxzV{V}}88nnߎߐPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMaEPMaEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM3PM3PMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QM_QM_QMkRM$kRMCRMCRM}SM}SMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Ke2t  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)=*=44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OMmOMTmOMOMOM-OM-OM?PM(?PMDPMDPM?LPM?LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM)4QM,)4QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 YG  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 YG  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 YG   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1F bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Qc  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR)B*B44>2?2IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$j%j'')Z*Z,,.J/J113:4:668*9*;;=>@@B C EEGGIrJrLLN^O^QQSJTJVVX6Y6[[]"^"``bceeggipjplln\o\qqsHtHvvx4y4{{} ~  nnZZБГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMUEPMUEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM/4QM,/4QMQMQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Z. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Z. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Z.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr"B b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1],{ >  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OMgOMTgOMOMOM'OM'OM?PM(?PMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PM-PM -PMiQM0 iQM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 XF bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 XF bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 XF  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 w? b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1,u>! a  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>&?&IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqvqvssu^v^xxzF{F}}..rrZZ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMUEPMUEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM6QM,6QM}QM}QM_RM$_RM7RM7RMqSMqSMTMTMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 3S@` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Jh7  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOMOMTOMOMOMQOMQOMEPM(EPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMQPM QPMQM0 QM-QMP-QM)4QM,)4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  I]@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  I]@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H|  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  I]@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <\ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Nj 0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM/4QM,/4QM QM QMRM$RM[RM[RMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Z" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Z" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Z"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 'Gq b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1E bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1V'x U  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  TT)>*>44>)?)IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''s s""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOMOMTOMOMOMKOMKOM?PM(?PMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PM9PM 9PMuQM0 uQM-QMP-QM6QM,6QMqQMqQMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  J\> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  J\> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H|  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  J\>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {&F b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18T"~  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 VvJj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Ik<  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMyOMyOMOMLOM[OMT[OMOMOMOMOMKPM(KPMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM)4QM,)4QMQMQMRM$RMaRMaRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 NE  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 NE  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 NE   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Kk:Z b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1[4   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN3?3IIS!T!^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGI[J[LLNIOIQQS7T7VVX%Y%[[]^``bcexexggifjfllnOoOqqs3t3vvxy{{}}mm߂߄QQÇÉ55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMyOMyOMOMLOM[OMT[OMOMOMOMOMEPM(EPMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM6QM,6QM1QM1QMqRM$qRMIRMIRMSMSM/TM/TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  ME  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  ME  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  ME   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~6V,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1f?q;{ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMٚOMٚOMwOMLwOM[OMT[OMOMOMOMOMPM(PMIEPMIEPM-LPM-LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 E  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 E  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 E   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Llg b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1\3 a 7 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  OO)9*944>%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMaOMTaOMOMOM!OM!OMKPM(KPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM/4QM,/4QMIQMIQMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @F  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @F  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @F   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1dH,P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMӚOMӚOMqOMLqOMaOMTaOMOMOM!OM!OMPM(PM=EPM=EPM3LPM3LPMUPM(UPMXPMXPMqnPMqnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM/4QM,/4QM QM QMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 F  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 F  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 F   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ;g b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1bD&P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMyOMyOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @F bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @F bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @F  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ii2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tX<4 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMӚOMӚOMqOMLqOMaOMTaOMOMOM!OM!OMPM(PMCEPMCEPM3LPM3LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM6QM,6QMQMQMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 E  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 E  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 E   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jL. } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>)?)IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpYqYssu=v=xxz!{!}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMoPM oPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 CE bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 CE bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 CE  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ii: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1o^M@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMǚOMǚOMeOMLeOMgOMTgOMOMOM'OM'OMPM(PM7EPM7EPM9LPM9LPMUPM(UPMXPMXPMknPMknPM PM PM PM  PMPM PMPML PM PM  PM'PM 'PMcQM0 cQM-QMP-QM54QM,54QMQMQMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y ) b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1mZG } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?Q@QBBD7E7GGIJLLNOQvQvSSU\V\XXZB[B]]_(`(bbdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMmOMTmOMOMOM-OM-OMQPM(QPMDPMDPM?LPM?LPMUPM(UPMXPMXPM#nPM#nPMPMPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RMgRMgRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 BE bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 BE bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 BE  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 |Jj&F b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<+  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)>*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM͚OM͚OMkOMLkOMgOMTgOMOMOM'OM'OMPM(PM=EPM=EPM9LPM9LPMUPM(UPMXPMXPMqnPMqnPMPMPM PM  PMPM PMPML PM PM  PMQPM QPMQM0 QM-QMP-QM6QM,6QMoQMoQMqRM$qRMIRMIRMSMSMTMTMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 H  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 H  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S'  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 H   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations14!{m } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  QQ)7*744>?IISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?/@/BBDEGGIIKdLdNNPFQFSSU(V(XXZ [ ]{]{__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOMMOMOM$OM{PM{PMEPMEPMoIPM$oIPMMnPMMnPMPMPMAPM$APM]PM]PMQMQM1QM 1QMQM| QMRM RMRM RMSM SMTM TMTUMTUMagUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1%Y] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1%Y] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1%Y] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations13S  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdnenggiXjXllnBoBqqs,t,vvxy{{}~uu__ԇԉII33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOM eOMIOMIOMPMPM1EPM1EPMLPMLPMenPMpenPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  aa)K*K44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44!!   ""$j%j'')T*T,,.>/>113(4(6689;;==?q@qBBD[E[GGIDJDLLN,O,QQSTVVXXZp[p]]_X`Xbbd@e@ggi(j(llnoqqssulvlxxzT{T}}<<$$ ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOMMOMOM$OMPMPMEPMEPMoIPM$oIPMSnPMSnPMPMPMAPM$APMiPMiPMQMQM1QM 1QMQM| QMRM RMsRM sRMSM SM}TM }TMMTUMMTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1&Z[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1&Z[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1&Z[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1:Z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)L*L44>4?4IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI8J8LLNOQQSTVwVwXXZ][]]]_C`Cbbd)e)ggijllnnphqhssuNvNxxz4{4}}ssYY̎̐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOM eOMCOMCOMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Ey b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  __)I*I44>1?1IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI1J1LLNOQQSSUpVpXXZV[V]]_<`v>xxz"{"}}xx\\ωϋBB(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM5OM 5OMOMOMcPMcPMEPMEPMoIPMoIPM5nPMp5nPMӮPMӮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1C} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1C} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1C  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  gg)S*S44>;?;IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG77##  "#%%'')q*q,,.]/]113I4I668595;;=>@@BCE{E{GGIcJcLLNKOKQQS3T3VVXY[[]^`w`wbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM͚OM͚OMkOM kOM1OM1OMPMPM7EPM7EPMLPMLPMknPMpknPM PM PMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>:?:IIS(T(^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGIbJbLLNPOPQQS>T>VVX,Y,[[]^``bceeggimjmllnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM/OM /OMOMOMcPMcPMEPMEPMoIPMoIPM5nPMp5nPMӮPMӮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1B} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1B} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1B  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  aa)I*I44>-?-IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55!!  } }""$e%e'')M*M,,.5/511346689;y;y==?]@]BBDAEAGGI%J%LLN O Q{Q{SSU_V_XXZC[C]]_'`'bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM͚OM͚OMkOM kOM7OM7OMPMPM=EPM=EPM LPM LPMqnPMpqnPMPMPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N" b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ZZ)D*D44>.?.IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppZZ D D  ..wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBDG?GIIS3T3^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssee W W  II;;--  "#%%'(*|*|,,.n/n113`4`668R9R;;=D>D@@B6C6EEG(H(JJLMOOQRT{T{VVXiYi[[]W^W``bCcCeeg-h-jjlmooqqsptpvvxVyV{{}<~<""xx\\ΑΓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM͚OM͚OMkOM kOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W) b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  dd)P*P44>:?:IIS"T"^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@44((  "#%%'(*~*~,,.j/j113V4V668B9B;;=.>.@@BCEEGHJzJzLLNbObQQSJTJVVX2Y2[[]^``bcevevggi^j^llnFoFqqs.t.vvxy{{}}rrZZ·ΉBB** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOM]PM]PMDPMDPMoIPMoIPM/nPMp/nPMͮPMͮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS!T!^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbddedggiJjJlln.o.qqstvvxxzc{c}}EE''yy[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMӚOMӚOMqOM qOM=OM=OMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)H*H44>.?.IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00    "#%t%t'')\*\,,.D/D113,4,6689;;==?p@pBBDXEXGGI>J>LLN"O"QQSTVxVxXXZ\[\]]_@`@bbd$e$ggijlzlznnp^q^ssuBvBxxz&{&}} ||``҉ҋDD(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM#OM #OMOMOMWPMWPMDPMDPM{IPM{IPM)nPMp)nPMǮPMǮPMMPMMPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Z} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Z} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Z  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  __)O*O44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??//  ""$w%w'')g*g,,.W/W113G4G668797;;='>'@@BCEEGHJ}J}LLNiOiQQSUTUVVXAYA[[]-^-``bceeghj{j{llngogqqsStSvvx?y?{{}+~+yyeeۑۓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMõPMõPMiPM`iPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`2 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ii  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  TT)>*>44>$?$IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiUU A A  --yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM#OM #OMOMOMQPMQPMDPMDPMIPMIPM#nPMp#nPMPMPMSPMSPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1[} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1[} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1[  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)E*E44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$W%W'')C*C,,.///11346689;};}==?i@iBBDUEUGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77{{cc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPMKPMKPMwnPMpwnPMPMPMõPMõPM{PM`{PMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  TT):*:44>?IISS]o^ohhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //ww] ]""$C%C''))*),,./11335h6h88:N;N==?0@0BBDEGGIIKeLeNNPGQGSSU)V)XXZ [ ]|]|__a^b^ddf@g@iik"l"nnpqsusuuuwWxWzz|9}9kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbdbebggiLjLlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMٚOMٚOMwOM wOM7OM7OMPMPMIEPMIEPM LPM LPM}nPMp}nPMPMPM۵PM۵PMiPM`iPMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i; b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMKPMKPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)@*@44>(?(IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$S%S'')=*=,,.'/'11346688:p;p==?Z@ZBBDDEDGGI,J,LLNOQQSSUkVkXXZQ[Q]]_7`7bbdeggijlvlvnnp\q\ssuBvBxxz({(}}ggډڋMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMٚOMٚOMwOM wOM7OM7OMPMPMIEPMIEPM LPM LPM}nPMp}nPMPMPM۵PM۵PMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1e  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMyOMyOMOM OMOMOMKPMKPMDPMDPMuIPMuIPMnPMpnPMPMPMGPMGPM9PM`9PMuQMuQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1W} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1W} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1W  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1 @  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>/?/IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbdSeSggi;j;lln#o#qqs t vvxxzg{g}}OOÂÄ77uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMoPM`oPMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rD b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Uu  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMuIPMuIPMnPMpnPMPMPMGPMGPMKPM`KPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SM)TMT )TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1X} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1X} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1X  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations15U  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  UU)=*=44>!?!IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMߚOMߚOM}OM }OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rF b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1p  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PM9PM`9PMuQMuQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1%E  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>;?;IIS'T'^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OM+OM+OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMϵPMϵPMKPM`KPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMłTMT łTMRUMRUMceUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1XT  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  XX)D*D44>.?.IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44((  "#%%'')r*r,,.^/^113J4J668696;;=">"@@BCEEGGInJnLLNVOVQQS>T>VVX&Y&[[]^``bbdjejggiRjRllnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMWPM`WPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Bb  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OM+OM+OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMϵPMϵPMoPM`oPMQMQM1QM1QMQML QMwRM wRMRMp RM}SMt }SMMTMT MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1}y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)<*<44>"?"IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI2J2LLNOQQSSUlVlXXZP[P]]_4`4bbdeggiiknlnnnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMmOMmOM OM  OMOMOM9PM9PMDPMDPMiIPMiIPM nPMp nPMPMPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1T} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1T} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1T  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)E*E44>3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqllnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMPMPMPM`PMKQMKQM1QM1QMQMT QMwRM wRMRMx RM}SM| }SMMTM\ MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V" b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1j  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10]]  RR)<*<44>"?"IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1]]II 5 5  !!  wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbdeggiikplpnnpVqVssu'?'IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMPMPMPM`PM9QM9QM1QM1QMQMT QMeRM eRMRMx RMkSM| kSMTM\ TMQUMQUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1X   b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  PP)6*644>?IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OM7OM7OMOM|OM9OM9OMoOMoOMOM|OM/OMH/OMPMPMDPMPDPM JPMX JPMAMPMAMPMVPMPVPMZPMZPMmPMmPMsPM$ sPMݳPM, ݳPMPM PMPM$ PMPM PMPM| PMiPMXiPMQMQM-QM-QM;QM;QMpQM\pQM7QM7QM5QM5QMRM8RMgRMgRMSMSMSMSMłTMlłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P{  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]}Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1GU?  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dGUc*q8Hh7V    d +  r  @  N/o bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa UU)K*K44>7?7IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I %%  " # %%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnOoOqqs7t7vvxy{{}~{{ccׇ׉KK33# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMmEPMmEPM!LPM!LPMUPM@UPMXPM XPMnPMnPM?PM?PMPM PM}PM }PMPMd PMPM PMPM PMQQMH QQM-QMh-QM ~  \, bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV) * 44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsqtqvvxWyW{{}=~=## {{__ёѓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM1OM1OMOM|OM9OM9OMoOMoOMOM|OM/OMH/OMPMPMDPMPDPM JPMX JPMAMPMAMPMVPMPVPMZPMZPMmPMmPMsPM$ sPMݳPM, ݳPMPM PMPM$ PMPM PMPM| PM9PMX9PMuQMuQM-QM-QM)?)IIS T ^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A ~~nn y y""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpeqessuIvIxxz-{-}}ggىًKK//# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMsEPMsEPM!LPM!LPMUPM@UPMXPM XPMnPMnPMEPMEPMPM PM}PM }PMPMd PMPM PMKPM KPMQMH QM-QMh-QM]0?0IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$_%_'')M*M,,.;/;11335u6u88:c;c=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ~~``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMgOMgOMOMdOMOOMlOOMOMOMOMOM9PM@9PMDPMDPM!LPM!LPMUPM@UPMXPM XPM nPM nPMPMPMPM PM}PM }PMPMd PMPM PMWPM WPMQMH QM-QMh-QM>HIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^JJ 6 6  ""nnX X""$B%B''),*,,,./11346u6u88:_;_==?G@GBBD-E-GGIIK\L\NNPBQBSSURVRXXZ8[8]]_`bbdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMgEPMgEPM!LPM!LPMUPM@UPMXPM XPMnPMnPM9PM9PMPM PM}PM }PMPMd PMPM PM!PM !PM]QMH ]QM-QMh-QM;QMD;QMpQMpQM7QM7QM5QM 5QMRMRMgRMpgRMSMtSMSMTSMTMTMTUM$TUMmgUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1GDU  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dGUc*q8g"F] T   b )  p  > ~  L bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)D*D44>4?4IIS T ^^hhrs} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln`o`qqsLtLvvx8y8{{}}pp\\rr^^ԑԓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMgOMgOMOMdOMOOMlOOMOMOMOMOM9PM@9PMDPMDPM!LPM!LPMUPM@UPMXPM XPM nPM nPMPMPMPM PM}PM }PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM>HISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$llR R""$8%8'')*,,./1w1w335]6]88:C;C==?'@'BBD E GzGzIIK1L1NNPQSSU V XXZ[]s]s__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMOOMlOOMOMOMOMOMPM@PMmEPMmEPM!LPM!LPMUPM@UPMXPM XPMnPMnPM?PM?PMPM PM}PM }PMPMd PMPM PMQPM QPMQMH QM-QMh-QM;QMD;QMpQMpQM7QM7QM5QM 5QMwRMwRMORMpORMSMtSMSMTSM}TM}TMMTUM$MTUMfUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1GU   b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dGUc*q8F T U    b L )   p  > ~ 3 s  L bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>&?&IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqzqzssubvbxxz{}}{{vv^^  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OM[OMT[OMOMOMOMOM?PM(?PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QME9QM,E9QMŎQMŎQMwRM$wRMORMORMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TG bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TG bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H|  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TG  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Vv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1'g bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1i4J  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)8*844>#?#IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!m m""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI3J3LLNOQQSTVwVwXXZ_[_]]_G`Gbbd/e/ggijllnnpsqsssu[v[xxzC{C}}++ss]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMaEPMaEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM3PM3PMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM!9QM,!9QMQMQMRM$RM[RM[RMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1? bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1m*g$   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMmOMmOM OML OM[OMT[OMOMOMOMOM?PM(?PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM;QM,;QMOQMOQMkRM$kRMCRMCRM}SM}SMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UG bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UG bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H|  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UG  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1  ` + v b } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL)6*644> ? IIST^w^whhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikelennpIqIssu-v-xxz{}}ggلنMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMaEPMaEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM3PM3PMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM;QM,;QM;QM;QMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1|  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1a  [  L  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOMmOMTmOMOMOM-OM-OMEPM(EPMDPMDPM?LPM?LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM99QM,99QMQMQMRM$RM[RM[RMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UI  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UI  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UI   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Vv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1V bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1N`)  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIUJULLNCOCQQS1T1VVXY[[] ^ ``bbdrerggi`j`llnIoIqqs-t-vvxy{{}}ggقلKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PM[EPM[EPMKLPMKLPMUPM(UPM YPM YPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM-9QM,-9QM;QM;QMRM$RM[RM[RMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 X. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 X. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 X.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .Na b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 J bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(k.qJ  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOMgOMTgOMOMOM'OM'OM?PM(?PMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PM?PM ?PM{QM0 {QM-QMP-QM;QM,;QMQMQMqRM$qRMIRMIRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TH bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TH bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TH  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1r ;  M 1q } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>!?!IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PM[EPM[EPMKLPMKLPMUPM(UPM YPM YPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM;QM,;QMQMQMkRM$kRMCRMCRM}SM}SM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 BbVv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations14 w : }  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMOMTOMOMOMQOMQOMKPM(KPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMoPM oPMQM0 QM-QMP-QME9QM,E9QMQMQMRM$RMaRMaRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  I_@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  I_@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  I_@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Xx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1\ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1p@` L } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  YY)E*E44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')s*s,,._/_113K4K668797;;=#>#@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMOEPMOEPMELPMELPMUPM(UPMYPMYPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QMK9QM,K9QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 X" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 X" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 X"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8Xv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 ` bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Nj P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  ZZ)L*L44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhZZ L L  >>00""  "#%%'')q*q,,.c/c113U4U668G9G;;=9>9@@B+C+EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3qqUUǑǓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMOMTOMOMOMKOMKOMEPM(EPMDPMDPM]LPM]LPMUPM(UPMYPMYPMnPMnPMPMPM/PM /PMPM PMPML PM1PM 1PMEPM EPMQM0 QM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  J^> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  J^> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  J^>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .N b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 0 P  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)=*=44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMUEPMUEPMELPMELPMUPM(UPMYPMYPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM;QM,;QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 e\| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 8  T "  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMaOMTaOMOMOM!OM!OMKPM(KPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM]9QM,]9QM͏QM͏QMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JG bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JG bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JG  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 DdZz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations12r bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1J% [  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbdeg{g{iikalannpGqGssu-v-xxz{}}ll߄߆RRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMߚOMߚOM}OML}OMaOMTaOMOMOM!OM!OMPM(PMIEPMIEPM3LPM3LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QMc9QM,c9QM͏QM͏QMRM$RMyRMyRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i=   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bbo b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations16v bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X1 c  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>8?8IIS$T$^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJxJxLLNdOdQQSPTPVVX?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMߚOMߚOM}OML}OMaOMTaOMOMOM!OM!OMPM(PMOEPMOEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM;QM,;QMiQMiQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 jb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<  n G o } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)>*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PM{PM {PMQM0 QM-QMP-QM{9QM,{9QMQMQMRM$RMaRMaRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @H bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @H bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @H  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Uu\| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1H bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 l R  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMӚOMӚOMqOMLqOMgOMTgOMOMOM'OM'OMPM(PMCEPMCEPM9LPM9LPMUPM(UPMXPMXPMwnPMwnPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM .QMP .QM{9QM,{9QMQMQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ddj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1L bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations10x \  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKlln5o5qqstvvx y {~{~}}hh݂݄RRLJlj<<&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMoPM oPMQM0 QM-QMP-QM!~ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMٚOMٚOMwOMLwOMgOMTgOMOMOM'OM'OMPM(PMIEPMIEPM9LPM9LPMUPM(UPMXPMXPM}nPM}nPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM .QMP .QM!'?'IIS T ^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnp[q[ssuAvAxxz'{'}} ffىًLL22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM9QM,9QM_QM_QMRM$RMmRMmRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @H bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @H bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @H  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 NnRr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1^ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xiZ K ^ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM͚OM͚OMkOMLkOMgOMTgOMOMOM'OM'OMPM(PM=EPM=EPM9LPM9LPMUPM(UPMXPMXPMqnPMqnPMPMPM PM  PMPM PMPML PM PM  PMWPM WPMQM0 QM-QMP-QM9QM,9QMeQMeQMRM$RMsRMsRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 G bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 G bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S'  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 G  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1b bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1wf U b } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<,,  "#%z%z'')f*f,,.R/R113>4>668*9*;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QME%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMӚOMӚOMqOMLqOMgOMTgOMOMOM'OM'OMPM(PMCEPMCEPM9LPM9LPMUPM(UPMXPMXPMwnPMwnPMPMPM PM  PMPM PMPML PM PM  PM]PM ]PMQM0 QM-QMP-QME^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Q  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1D 3 " Q } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)>*>44>$?$IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**r r""$Z%Z'')B*B,,.*/*11346688:n;n==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp>  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMGOMGOMOM$OMuPMuPMEPMEPMoIPM$oIPMGnPMGnPMPMPMAPM$APMiPMiPMQMQM1QM 1QMQM| QMRM RMRM RMSM SMTM TMTUMTUMagUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1!U_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1!U_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1!U_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1:Z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  nn)Z*Z44>D?DIIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ>>22  "&#&%%'(**,,.t/t113`4`668L9L;;=8>8@@B$C$EEGHJJLLNlOlQQSTTTVVXI?IIIS5T5^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uugg Y Y  KK==//!!  "#%%'(*~*~,,.p/p113b4b668T9T;;=F>F@@B8C8EEG*H*JJLMOOQRT}T}VVXkYk[[]Y^Y``bEcEeeg/h/jjlmooqqsrtrvvxXyX{{}>~>$$zz^^БГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMGOMGOMOM$OM{PM{PMEPMEPMoIPM$oIPMMnPMMnPMPMPMAPM$APMoPMoPMQMQM1QM 1QMQM| QMRM RMsRM sRMSM SMqTM qTMATUMATUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1"V] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1"V] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1"V] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)P*P44>6?6IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%|%|'')d*d,,.L/L1134446689;;=>@x@xBBD`E`GGIFJFLLN*O*QQSTVVXXZd[d]]_H`Hbbd,e,ggijllnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1G{ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  cc)Q*Q44>=?=IIS%T%^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uucc Q Q  ??--   ""$n%n'')\*\,,.J/J113848668&9&;;=>@@BCEyEyGGIeJeLLNOOOQQS9T9VVX#Y#[[] ^ ``bbdhehggiNjNlln2o2qqstvvxxzg{g}}II++ }}__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM;OM ;OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ^^)H*H44>.?.IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##m m""$W%W'')A*A,,.+/+11346688:t;t==?Z@ZBBD@E@GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpVqVssu???IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11!!  "#%y%y'')i*i,,.Y/Y113I4I668999;;=)>)@@BCEEG H JJLLNkOkQQSWTWVVXCYC[[]/^/``bceeghj}j}llnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM5OM 5OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSUMSUMwfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  \\)B*B44>$?$IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##  e e""$K%K'')1*1,,./11335p6p88:V;V==?8@8BBDEGGIIKmLmNNPOQOSSU1V1XXZ[]]__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMӚOMӚOMqOM qOM1OM1OMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])I*I44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$[%['')G*G,,.3/31134668 9 ;;==?m@mBBDYEYGGICJCLLN+O+QQSTVVXXZo[o]]_W`Wbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM/OM /OMOMOMcPMcPMEPMEPMoIPMoIPM5nPMp5nPMӮPMӮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  __)I*I44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22  ~ ~""$h%h'')R*R,,.e>ggi&j&llnoqqssujvjxxzR{R}}::"" jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMӚOMӚOMqOM qOM=OM=OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>5?5IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI]J]LLNGOGQQS1T1VVXY[[]^`z`zbbddedggiNjNlln8o8qqs"t"vvx y {{}}kkUUʇʉ??)) b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM/OM /OMOMOM]PM]PMDPMDPMuIPMuIPM/nPMp/nPMͮPMͮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>-?-IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?[@[BBDEEEGGI-J-LLNOQQSSUlVlXXZR[R]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXˉˋ>>$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMٚOMٚOMwOM wOM=OM=OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ZZ)D*D44>,?,IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  l l""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI0J0LLNOQQSSUoVoXXZU[U]]_;`;bbd!e!ggijlzlznnp`q`ssuFvFxxz,{,}}kkމދQQĎĐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOM]PM]PMDPMDPM{IPM{IPM/nPMp/nPMͮPMͮPMMPMMPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1V} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1V} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1V  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>8?8IIS&T&^^h i s|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI`J`LLNNONQQS1?1IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==--  "#%{%{'')g*g,,.S/S113?4?668+9+;;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99ww b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOMWPMWPMDPMDPM{IPM{IPM)nPMp)nPMǮPMǮPMMPMMPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1W} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1W} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1W  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  VV)@*@44>*?*IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llVV @ @  **ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLN O QQSSUkVkXXZU[U]]_?`?bbd)e)ggijllnnplqlssuPvPxxz4{4}}nnRRĎĐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMٚOMٚOMwOM wOM%OM%OMPMPMIEPMIEPMKPMKPM}nPMp}nPMPMPMɵPMɵPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1e  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)A*A44>%?%IIS T ^{^{hhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==-- u u""$]%]'')E*E,,.-/-11346688:q;q==?U@UBBD9E9GGIJLLNOQsQsSSUWVWXXZ;[;]]_`bbdeguguiikYlYnnp=q=ssu!v!xxz{}w}w[[̈́͆== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM#OM #OMOMOMWPMWPMDPMDPMoIPMoIPM)nPMp)nPMǮPMǮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>22&&  "#%%'(*|*|,,.h/h113T4T668@9@;;=,>,@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPM{PM`{PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k?  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k?  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k?  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1[{  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  [[)M*M44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii[[ M M  ??11##  "#%%'')r*r,,.d/d113V4V668H9H;;=:>:@@B,C,EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)D*D44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$p%p'')X*X,,.@/@113(4(6689;;==?l@lBBDTETGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1r  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPM3PM`3PMoQMoQM1QM1QMQML QMwRM wRMORMp ORMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1S} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1S} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1S  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1;  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>"?"IIST^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMPMPM{PM`{PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tH b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1`  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMyOMyOMOM OMOMOMKPMKPMDPMDPMoIPMoIPMnPMpnPMPMPMAPMAPMKPM`KPMQMQM1QM1QMQML QM_RM _RM7RMp 7RMqSMt qSMTMT TMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1T} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1T} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1T  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations10P  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]k^khhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMyOMyOMOM OMOMOMEPMEPMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PM3PM`3PMoQMoQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1 @  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>&?&IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OM%OM%OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMɵPMɵPMKPM`KPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMłTMT łTMRUMRUMceUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1YU  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>)?)IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIQJQLLN;O;QQS%T%VVXY[[]]_n`nbbdXeXggiBjBlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMQPM`QPMQMQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1=]  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OM%OM%OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMɵPMɵPMuPM`uPMQMQM1QM1QMQML QMwRM wRMRMp RM}SMt }SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844> ? IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMPMPM PM` PMEQMEQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMEeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1c  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)G*G44>/?/IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11!!   ""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMmOMmOM OM  OMOMOM?PM?PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMPM`PMPMPM1QM1QMQML QM}RM }RMRMp RMSMt SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1H| b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)8*844>"?"IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnppqpssuTvTxxz8{8}}rrVVȎȐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMPMPM PM` PMEQMEQM1QM1QMQMT QMqRM qRMRMx RMwSM| wSM/TM\ /TM%RUM%RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)=*=44>!?!IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!  i i""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OM7OM7OMOM|OM9OM9OMoOMoOMOM|OM/OMH/OM PM PMDPMPDPM JPMX JPMAMPMAMPMVPMPVPMZPMZPMmPMmPMyPM$ yPMݳPM, ݳPMPM PMPM$ PMPM PMPM| PMcPMXcPMQMQM-QM-QM9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ? {{kkw w""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllnoooqqs[t[vvxGyG{{}3~3 mm# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMUOMlUOMOMOMOMOMPM@PMsEPMsEPM'LPM'LPMUPM@UPMXPM XPMnPMnPMEPMEPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/911335r6r88:`;`=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnXoXqqs>""  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM7OM7OMOM|OM9OM9OMoOMoOMOM|OM/OMH/OMPMPMDPMPDPM JPMX JPMAMPMAMPMVPMPVPMZPMZPMmPMmPMsPM$ sPMݳPM, ݳPMPM PMPM$ PMPM PMPM| PMQPMXQPMQMQM-QM-QM?+?+IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7 llXXqq] ]""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoqqssuovoxxzW{W}}??''kk# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM OM OMOMdOMUOMlUOMOMOMOMOMPM@PMyEPMyEPM'LPM'LPMUPM@UPMXPM XPMnPMnPMKPMKPMPM PMPM PMPMd PMPM PMPM PMWQMH WQM-QMh-QM3$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$?%?''))*),,./1[1[335E6E88:/;/==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMmOMmOM OMd OMUOMlUOMOMOMOMOM?PM@?PMDPMDPM'LPM'LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PMuPM uPMQMH QM-QMh-QM )?)IrIrST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGIQJQLLN;O;QQS%T%VnVnXXZX[X]]_B`BbbdXeXggiBjBlln6o6qqs t vvx y {{}}iiނބSSȇȉ==''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMUOMlUOMOMOMOMOMPM@PMmEPMmEPM'LPM'LPMUPM@UPMXPM XPMnPMnPM?PM?PMPM PMPM PMPMd PMPM PMKPM KPMQMH QM-QMh-QM 2?2IIST^^hhrxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln@o@qqs(t(vvxy{X{X}}@@((ȇȉ<<$$  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMmOMmOM OMd OMUOMlUOMOMOMOMOM?PM@?PMDPMDPM'LPM'LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PMWPM WPMQMH QM-QMh-QM  ? IfIfST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSU6V6XXZ[]]_`bbdeggiiknlnnnp\q\ssuBvBxxz({(}}ggډڋMM33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMUOMlUOMOMOMOMOMPM@PMmEPMmEPM'LPM'LPMUPM@UPMXPM XPMnPMnPM?PM?PMPM PMPM PMPMd PMPM PM!PM !PM]QMH ]QM-QMh-QM $?$IIST^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpXqXssu>""  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOM[OMT[OMOMOMOMOMEPM(EPMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM#4QM,#4QMQMQM}RM$}RMURMURMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TI bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TI bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TI  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t8 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<x4   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)?*?44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33##  ""$q%q'')]*],,.I/I113545668!9!;;= > @@BBDiEiGGIQJQLLN9O9QQS!T!VVX Y [}[}]]_e`ebbdMeMggi5j5llnoqqstvyvyxxza{a}}II11qq b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMgEPMgEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM9PM9PMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM#4QM,#4QMQMQMqRM$qRMIRMIRMSMSMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 SsFf b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1C bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@}:   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMsOMsOMOMLOM[OMT[OMOMOMOMOM?PM(?PMDPMDPM-LPM-LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QM9QM9QMeRM$eRM=RM=RMwSMwSM#TM#TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UI bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UI bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UI  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Nn b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1| bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1p,h$L  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)7*744>?IIST^s^shhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$S%S'');*;,,.#/#113 4 6688:g;g==?M@MBBD1E1GGIJLLNNPkQkSSUOVOXXZ3[3]]_`bbddfmgmiikQlQnnp5q5ssuvxxzz|o}oSSńņ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMgEPMgEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM9PM9PMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QM?QM?QMYRM$YRM1RM1RMkSMkSMہTMہTMSUMSUMSfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 L bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 L bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,L: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1w4q.P  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  LL)2*244>?IISS]i^ihhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ooU U""$;%;'')!*!,,./1z1z335`6`88:F;F==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3gg׋׍GG b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMmOMTmOMOMOM-OM-OMKPM(KPMDPMDPM?LPM?LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PM-PM -PMiQM0 iQM-QMP-QM#4QM,#4QMoQMoQMRM$RMgRMgRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 QK  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 QK  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 QK   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 w> b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1GU  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>9?9IIS%T%^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMOOQQSmTmVVX[Y[[[]I^I``b5c5eeghjjl m o|o|qqsbtbvvxHyH{{}.~.llތގPP‘“ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PM[EPM[EPMKLPMKLPMUPM(UPM YPM YPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM#4QM,#4QM3QM3QMRM$RM[RM[RMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 V. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 V. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 V.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Llp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1E O@  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMmOMTmOMOMOM-OM-OMEPM(EPMDPMDPM?LPM?LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 PJ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 PJ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 PJ  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1c*q G  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln"o"qqstvuvuxxzW{W}}99ooQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMaEPMaEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM3PM3PM#PM #PMPM PMPML PM%PM %PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1['  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Qq< b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Yc   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>#?#IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikhlhnnpLqLssu0v0xxz{}}jj܄܆PPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOMOMOMQOMQOMKPM(KPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMPMPM5PM 5PMPM PMPML PM7PM 7PM9PM 9PMuQM0 uQM-QMP-QM)4QM,)4QM#QM#QMRM$RMsRMsRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ia@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ia@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ia@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1R$v0 p  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)C*C44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')[*[,,.K/K113;4;668+9+;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMUEPMUEPMELPMELPMUPM(UPMYPMYPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM)4QM,)4QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 V" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 V" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 V"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rry b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P p 0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMOMTOMOMOMQOMQOMKPM(KPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  J`> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  J`> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  J`>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Hl>  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$M%M'')9*9,,.%/%11346688:s;s==?_@_BBDKEKGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PM[EPM[EPMELPMELPMUPM(UPMYPMYPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM6QM,6QMwQMwQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >l b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@`0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM#OML#OMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMEPM EPMQM0 QM-QMP-QM/4QM,/4QM׎QM׎QMRM$RMgRMgRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 FI bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 FI bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 FI  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }*J b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]:  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln0o0qqstvvxy{y{y}}cc؂؄MM‡‰77!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMߚOMߚOM}OML}OMgOMTgOMOMOM'OM'OMPM(PMOEPMOEPM9LPM9LPMUPM(UPMXPMXPMnPMnPM!PM!PM PM  PMPM PMPML PM PM  PMPM PMQM0 QM.QMP.QM/4QM,/4QMQMQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kA   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 rXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1[6  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJvJvLLN^O^QQSFTFVVX.Y.[[]^``bbdrerggiZjZllnBoBqqs*t*vvxy{{}}nnVVʇʉ>>&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMoPM oPMQM0 QM-QMP-QM6QM,6QMyQMyQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 EI bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 EI bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 EI  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tQ. } } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}cc։֋II// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMgOMTgOMOMOM'OM'OMPM(PMUEPMUEPM9LPM9LPMUPM(UPMXPMXPMnPMnPM'PM'PM PM  PMPM PMPML PM PM  PMPM PMQM0 QM .QMP .QM6QM,6QM7QM7QM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1  @m b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lG"};{ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)@*@44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$l%l'')T*T,,.>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMgRMgRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0PZz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1aB# ` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMIEPMIEPM?LPM?LPMUPM(UPMXPMXPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM/4QM,/4QMOQMOQMRM$RM[RM[RMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`6  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1fL2P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM5TM5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 KkVv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1eF' } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>!?!IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMߚOMߚOM}OML}OMmOMTmOMOMOM-OM-OMPM(PMOEPMOEPM?LPM?LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSMTMTMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 !A b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1~dJ6 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]m^mhhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?.@.BBDEGGIIKcLcNNPEQESSU'V'XXZ [ ]z]z__a\b\ddf>g>iik l nnpqssssuuwUxUzz|7}7kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM)OML)OMmOMTmOMOMOM-OM-OM]PM(]PMDPMDPM?LPM?LPMUPM(UPMXPMXPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM54QM,54QMӏQMӏQMRM$RMRMRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ss6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lXD } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMӚOMӚOMqOMLqOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMmRMmRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1qbS@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  WW)A*A44>,?,IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::** v v""$`%`'')J*J,,.4/411346689;};}==?g@gBBDQEQGGI1?1IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMٚOMٚOMwOMLwOMmOMTmOMOMOM-OM-OMPM(PMCEPMCEPM?LPM?LPMUPM(UPMXPMXPMwnPMwnPMPMPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 3 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1D5& } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>'?'IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnTTljNj::  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMGOMGOMOM$OMuPMuPMEPMEPMoIPM$oIPMGnPMGnPMPMPMAPM$APMoPMoPMQMQM1QM 1QMQM| QMRM RMRM RMSM SM%TM %TMTUMTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Qa b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Qa b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Qa b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)X*X44>F?FIIS2T2^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%%'')p*p,,.`/`113P4P668@9@;;=0>0@@B C EEGHJJLLNrOrQQS^T^VVXJYJ[[]6^6``b"c"eeghjjllnpopqqs\t\vvxHyH{{}4~4  nn b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PM%PM%PM1QM1QMQML QMRM RMRMp RMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I} b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>=?=IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIeJeLLNSOSQQSATAVVX/Y/[[]^``b c eeggipjpllnYoYqqs=t=vvx!y!{{}~ww[[͇͉??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMAOMAOMOM$OMuPMuPMEPMEPMoIPM$oIPMGnPMGnPMPMPMAPM$APMuPMuPMQMQM1QM 1QMQM| QMRM RMRM RMSM SMTM TM}TUM}TUM%gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Hh  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$`%`'')L*L,,.8/8113$4$6689;;==?r@rBBD^E^GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMӚOMӚOMqOM qOMCOMCOMPMPM=EPM=EPMLPMLPMqnPMpqnPMPMPMPMPMPM`PM%PM%PM1QM1QMQML QMRM RMsRMp sRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1I}! b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ]])G*G44>1?1IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss]] G G  11zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUrVrXXZ\[\]]_F`Fbbd0e0ggijllnoqsqsssuWvWxxz;{;}}uuYYˎː== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM;OM ;OMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMcPM`cPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1:Z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdkekggiUjUlln?o?qqs)t)vvxy{{}}rr\\чщFF00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMӚOMӚOMqOM qOM1OM1OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  gg)S*S44>=?=IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC77++  "#%%' ( **,,.m/m113Y4Y668E9E;;=1>1@@BCEEG H J}J}LLNeOeQQSMTMVVX5Y5[[]^``bceyeyggiajallnIoIqqs1t1vvxy{{}~uu]]чщEE-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM;OM ;OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMuPM`uPMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Kk  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)I*I44>1?1IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI5J5LLNOQQSTVtVtXXZZ[Z]]_@`@bbd&e&ggi j llnnpeqessuKvKxxz1{1}}ppVVɎɐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMٚOMٚOMwOM wOM1OM1OMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)K*K44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33##  "#%w%w'')_*_,,.G/G113/4/6689;;==?s@sBBD[E[GGIAJALLN%O%QQS T V{V{XXZ_[_]]_C`Cbbd'e'ggi j l}l}nnpaqassuEvExxz){)}} ccՉՋGG++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)P*P44>8?8IIS T ^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD44   " # %%'')n*n,,.Z/Z113F4F668292;;=>@@BCExExGGI`J`LLNHOHQQS0T0VVXY[[]^`t`tbbd\e\ggiDjDlln,o,qqstvvxxzp{p}}XX̂̄@@%% ~~ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMٚOMٚOMwOM wOM7OM7OMPMPMIEPMIEPM LPM LPM}nPMp}nPMPMPM۵PM۵PMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1\|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  WW)A*A44>'?'IIS T ^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llXX D D  00||f f""$P%P''):*:,,.$/$11346688:m;m==?S@SBBD9E9GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiikilinnpOqOssu5v5xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ^^)F*F44>*?*IIST^^hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22 z z""$b%b'')J*J,,.2/211346689;v;v==?Z@ZBBD>E>GGI"J"LLNOQxQxSSU\V\XXZ@[@]]_$`$bbdegzgziik^l^nnpBqBssu&v&xxz { }|}|``҄҆BB$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMٚOMٚOMwOM wOM7OM7OMPMPMIEPMIEPM LPM LPM}nPMp}nPMPMPM۵PM۵PMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1g  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  WW)=*=44>?IIST^r^rhhrRsR} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22zz` `""$F%F''),*,,,./11335k6k88:Q;Q==?3@3BBDEGGIIKhLhNNPJQJSSU,V,XXZ[]]__aabaddfCgCiik%l%nnpqsxsxuuwZxZzz|<}<nnދލNN b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM/OM /OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1R} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1R} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1R  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  bb)T*T44>D?DIIS0T0^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppbb T T  FF88**  "#%%'(*y*y,,.k/k113]4]668O9O;;=A>A@@B3C3EEG%H%JJLMOOQRTxTxVVXfYf[[]T^T``b@c@eeg*h*jjlmooqqsmtmvvxSyS{{}9~9uuYYˑ˓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMߚOMߚOM}OM }OM%OM%OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMɵPMɵPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1c  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  XX)B*B44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++ w w""$a%a'')K*K,,.5/51134668 9 ;~;~==?h@hBBDRERGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM)OM )OMOMOM]PM]PMDPMDPM{IPM{IPM/nPMp/nPMͮPMͮPMMPMMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1S} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1S} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1S  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIST^^hispsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdaeaggiGjGlln+o+qqs t v~v~xxz`{`}}BB$$vvXX b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMߚOMߚOM}OM }OM%OM%OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMɵPMɵPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d< b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1r  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  VV)@*@44>(?(IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //{{e e""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikmlmnnpQqQssu5v5xxz{}}ooSSƉƋ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM)OM )OMOMOM]PM]PMDPMDPMuIPMuIPM/nPMp/nPMͮPMͮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)L*L44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$t%t'')d*d,,.T/T113D4D668494;;=$>$@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM#OM #OMOMOMWPMWPMDPMDPMoIPMoIPM)nPMp)nPMǮPMǮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$T%T'')@*@,,.,/,11346689;z;z==?f@fBBDRERGGI%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM#OM #OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1O} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1O} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1O  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMPMPM{PM`{PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vL b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMQPMQPMDPMDPMoIPMoIPM#nPMp#nPMPMPMAPMAPMPM`PM PM PM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMPMPMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vN b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vN b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vN b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMKPMKPMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PM3PM`3PMoQMoQM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1;  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDlElGGITJTLLN?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?G@GBBD-E-GGIJLLNNPlQlSSURVRXXZ8[8]]_`bbdeggiikglgnnpMqMssu3v3xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMyOMyOMOM OMOMOMKPMKPMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMQPM`QPMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SM)TMT )TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations18X  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44>?IIST^x^xhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PM PM PM1QM1QMQML QM_RM _RM7RMp 7RMqSMt qSMTMT TMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]n^nhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?'@'BBD E GzGzIIK\L\NNP>Q>SSU V XXZ[]s]s__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMsOMsOMOM OMOMOMEPMEPMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%}%}'')o*o,,.a/a113S4S668E9E;;=7>7@@B)C)EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m ooqqsotovvxUyU{{};~;!!ww[[͓͑ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMPMPMPM`PM?QM?QM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM3eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1\  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  LL)@*@44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //  k k""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`MbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%%mm b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMsOMsOMOM OMOMOM?PM?PMDPMDPMcIPMcIPMnPMpnPMPMPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMyRUMyRUM!eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1J~ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)B*B44>.?.IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln/o/qqstvvxxzd{d}}FF(( zz\\ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM OM OMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMPMPMPM`PMKQMKQM1QM1QMQMT QM}RM }RMRMx RMSM| SMMTM\ MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  JJ)<*<44>$?$IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD4?4IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : : qq__{{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjglln\o\qqs@t@vvx$y${{}~zz^^ЇЉBB&&# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM OM OMOMdOMUOMlUOMOMOMOMOMPM@PMyEPMyEPM'LPM'LPMUPM@UPMXPM XPMnPMnPMKPMKPMPM PMPM PMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QM 5?5IIS!T!^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$m%m'')]*],,.M/M11346688:w;w=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjsllnkokqqsWtWvvxCyC{{}/~/}}iiߑߓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM7OM7OMOM|OM?OM?OMuOMuOMOM|OM5OMH5OM PM PMDPMPDPMJPMXJPMGMPMGMPMVPMPVPMZPMZPMmPMmPMyPM$ yPMPM, PMPM PMPM$ PMPM PMPM| PM'PMX'PMcQMcQM-QM-QMi  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1dH L  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1ddH,tX< dF  @ (   >  l  N  0z 8x| bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^ HH):*:44>&?&IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^HH 2 2 x xbbLLeeO O""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnoqtqtssuXvXxxz<{<}} vvZZ̎̐>># b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMUOMlUOMOMOMOMOMPM@PMyEPMyEPM'LPM'LPMUPM@UPMXPM XPMnPMnPMKPMKPMPM PMPM PMPMd PMPM PMPM PM?QMH ?QM-QMh-QM )?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$O%O'');*;,,.'/'1n1n335Z6Z88:F;F==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMsOMsOMOMdOM[OMl[OMOMOMOMOMEPM@EPMDPMDPM-LPM-LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PM{PM {PMQMH QM-QMh-QM.?.ItItST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22&&  "#%%'')p*p,,.\/\113H4H668494;;= > @@B C EEGGInJnLLNVOVQQS>T>VVXXZl[l]]_T`TbbdjejggiRjRllnDoDqqs,t,vvxy{{}}ppXẊ̉@@((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM[OMl[OMOMOMOMOMPM@PMsEPMsEPM-LPM-LPMUPM@UPMXPM XPMnPMnPMEPMEPMPM PMPM PMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QM-?-IIST^^hhrxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln2o2qqstvvxy{M{M}}77!!ćĉ99##  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMsOMsOMOMdOM[OMl[OMOMOMOMOM?PM@?PMDPMDPM-LPM-LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PMQPM QPMQMH QM-QMh-QM  T T bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR):*:44>"?"IeIeST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$f%f'')N*N,,.6/611346689;z;z==?b@bBBDJEJGGI2J2LLNOQQSSU=V=XXZ![!]]_`bbdeggiiknlnnnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM OM OMOMdOM[OMl[OMOMOMOMOMPM@PMsEPMsEPM-LPM-LPMUPM@UPMXPM XPMnPMnPMEPMEPMPM PMPM PMPMd PMPM PMPM PMKQMH KQM-QMh-QM"?"IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD?IIST^u^uhhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$C%C'')-*-,,./11346v6v88:`;`==?H@HBBD.E.GGIJLLNNPmQmSSUSVSXXZ9[9]]_`bbdegxgxiik^l^nnpDqDssu*v*xxz{}}ii܄܆OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMaOMTaOMOMOM!OM!OMPM(PMgEPMgEPM3LPM3LPMUPM(UPMXPMXPMnPMnPM9PM9PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM39QM,39QM_QM_QMRM$RM[RM[RMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 c.N b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18}B n  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMaOMTaOMOMOM!OM!OMEPM(EPMDPMDPM3LPM3LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMPM PMKQM0 KQM-QMP-QM;QM,;QM5QM5QMYRM$YRM1RM1RMkSMkSMہTMہTMSUMSUMSfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UK bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UK bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UK  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1v  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X  T  F  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  JJ)0*044>?IISS]g^ghhrIsI} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%mmS S""$9%9'')*,,./1x1x335^6^88:D;D==?(@(BBD E G{G{IIK]L]NNP?Q?SSU!V!XXZ[]t]t__aVbVddf8g8iiklnnpprmsmuuwOxOzz|1}1eeՋՍEE b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMgOMTgOMOMOM'OM'OMPM(PMmEPMmEPM9LPM9LPMUPM(UPMXPMXPMnPMnPM?PM?PM PM  PMPM PMPML PM PM  PMQPM QPMQM0 QM-QMP-QM;QM,;QMQMQMkRM$kRMCRMCRM}SM}SM#TM#TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 o;[. b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1L  V  3 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)9*944>?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMmOMTmOMOMOM-OM-OMQPM(QPMDPMDPM?LPM?LPMUPM(UPMXPMXPM#nPM#nPMPMPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM39QM,39QMQMQM}RM$}RMURMURMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  MM  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  MM  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  MM   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 > b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18J  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>$?$IIS T ^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hbbd0e0ggijllnoqtqtssu\v\xxzD{D}},,tt^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMaEPMaEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QMK9QM,K9QM%QM%QMRM$RMmRMmRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1['  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1$d bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`0 4t } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMyOMyOMOMLOMmOMTmOMOMOM-OM-OMKPM(KPMDPMDPM?LPM?LPMUPM(UPMXPMXPMnPMnPMPMPMPM PMPM PMPML PMPM PMPM PMWQM0 WQM-QMP-QM;QM,;QMQMQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  LL bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  LL bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  LL  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 m * b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1\ % n 7 W } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>!?!IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikflfnnpJqJssu.v.xxz{}}hhڄچNN44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMgEPMgEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM9PM9PM#PM #PMPM PMPML PM%PM %PMuPM uPMQM0 QM-QMP-QM;QM,;QMQMQM}RM$}RMURMURMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t8` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 P p @  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM#OML#OMOMTOMOMOMQOMQOMWPM(WPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM)nPM)nPMǮPMǮPM5PM 5PMPM PMPML PM7PM 7PM3PM 3PMoQM0 oQM-QMP-QMQ9QM,Q9QMIQMIQMRM$RMaRMaRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ic@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ic@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ic@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 < b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1$d bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d8 T } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PM[EPM[EPMELPMELPMUPM(UPMYPMYPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QMc9QM,c9QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 T" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 T" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 T"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 *J| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1:z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hC y < } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$o%o'')_*_,,.O/O113?4?668/9/;;=>@@BCEEGGIwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMQOMQOMQPM(QPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM#nPM#nPMPMPM5PM 5PMPM PMPML PM7PM 7PM-PM -PMiQM0 iQM-QMP-QM;QM,;QMߏQMߏQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jb> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jb> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jb>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r4 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 ` 4  \ ( } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMaEPMaEPMELPMELPMUPM(UPMYPMYPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QM;QM,;QMQMQMRM$RM[RM[RMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y"Bo b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T / e  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)=*=44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM)OML)OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QMi9QM,i9QMQMQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 BK bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 BK bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 BK  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 : b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1:z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hG&  Z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  ZZ)F*F44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln>o>qqs&t&vvxy{{}}jjނބRRƇƉ::"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMmOMTmOMOMOM-OM-OMPM(PMUEPMUEPM?LPM?LPMUPM(UPMXPMXPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM9QM,9QMQMQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mE  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 (Hu b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@& r  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  UU)C*C44>1?1IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd`e`ggiJjJlln4o4qqstvvxy{}{}}}gg܂܄QQƇƉ;;%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d C "   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)>*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMmOMTmOMOMOM-OM-OMPM(PM[EPM[EPM?LPM?LPMUPM(UPMXPMXPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QM' $ f } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)<*<44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM/OML/OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QMu9QM,u9QMcQMcQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @L bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @L bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @L  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ww8 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1B bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1kN 1 b } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMߚOMߚOM}OML}OMmOMTmOMOMOM-OM-OMPM(PMOEPMOEPM?LPM?LPMUPM(UPMXPMXPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMEPM EPMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 &F b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1T bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P8  $ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99 yy b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d>   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1<  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 p X @ ( } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  UU)=*=44>#?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbdegsgsiikWlWnnp;q;ssuvxxz{}u}uYY˄ˆ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM/OML/OMsOMTsOMOMOM3OM3OMcPM(cPMEPMEPMELPMELPMUPM(UPMYPMYPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM9QM,9QM)QM)QMRM$RMmRMmRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @L bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @L bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @L  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Xx6 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1X bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`N< * (h } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMٚOMٚOMwOMLwOMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 K bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 K bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 < b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1j bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(    } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  ]])O*O44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk]] O O  AA33%%  " # %%'')t*t,,.f/f113X4X668J9J;;=<><@@B.C.EEG H JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM/OML/OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM?%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMߚOMߚOM}OML}OMsOMTsOMOMOM3OM3OMPM(PMIEPMIEPMELPMELPMUPM(UPMYPMYPM}nPM}nPMPMPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QMQ3?3IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!uuWW b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMMOMMOMOM$OM{PM{PMEPMEPMuIPM$uIPMMnPMMnPMPMPMGPM$GPMuPMuPMQMQM1QM 1QMǀQM| ǀQMRM RMRM RMSM SM݂TM ݂TMTUMTUMUgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Me b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Me b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Me b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Hh  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>A?AIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIiJiLLNWOWQQSETEVVX3Y3[[]!^!``bceeggitjtlln]o]qqsAtAvvx%y%{{} ~ {{__чщCC'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMӚOMӚOMqOM qOMCOMCOMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPMPM`PM%PM%PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SM%TMT %TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)T*T44>B?BIIS.T.^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44$$  "#%|%|'')l*l,,.\/\113L4L668<9<;;=,>,@@BCEEG H JJLLNnOnQQSZTZVVXFYF[[]2^2``bceeg h jjllnlolqqsXtXvvxDyD{{}0~0~~jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMGOMGOMOM$OMuPMuPMEPMEPMuIPM$uIPMGnPMGnPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMyRM yRMSM SMTM TMSTUMSTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Na b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Na b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Na b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  __)I*I44>3?3IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uu__ I I  33||f f""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUtVtXXZ^[^]]_H`Hbbd2e2ggijllnoququssuYvYxxz={=}}!!ww[[͎͐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMٚOMٚOMwOM wOMCOMCOMPMPMCEPMCEPMLPMLPMwnPMpwnPMPMPMPMPMPM`PM%PM%PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K% b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K% b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K% b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)L*L44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$^%^'')J*J,,.6/6113"4"6689;;==?p@pBBD\E\GGIFJFLLN.O.QQSTVVXXZr[r]]_Z`ZbbdBeBggi*j*llnoqqssunvnxxzV{V}}>>&&jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOMuPMuPMEPMEPMoIPMoIPMGnPMpGnPMPMPMAPMAPMoPM`oPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Aa  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  kk)W*W44>A?AIIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG;;//  "###%%'(**,,.q/q113]4]668I9I;;=5>5@@B!C!EEG H JJLLNiOiQQSQTQVVX9Y9[[]!^!``b c e}e}ggiejellnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMٚOMٚOMwOM wOM1OM1OMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMյPMյPMPM`PM%PM%PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>8?8IIS"T"^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGI`J`LLNJOJQQS4T4VVXY[[]^`}`}bbdgegggiQjQlln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMAOM AOMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPM{PM`{PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Pp  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)M*M44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%y%y'')a*a,,.I/I1131416689;;=>@u@uBBD]E]GGICJCLLN'O'QQS T V}V}XXZa[a]]_E`Ebbd)e)ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMٚOMٚOMwOM wOM1OM1OMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMյPMյPMPM`PM%PM%PM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T. b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])G*G44>/?/IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd$e$ggi j l}l}nnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM;OM ;OMOMOMoPMoPM EPM EPMuIPMuIPMAnPMpAnPM߮PM߮PMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>+?+IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?W@WBBD=E=GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikmlmnnpSqSssu9v9xxz{}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]5 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1i  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)L*L44>4?4IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@00  "#%~%~'')j*j,,.V/V113B4B668.9.;;=>@@BCEtEtGGI\J\LLNDODQQS,T,VVXY[[]]_p`pbbdXeXggi@j@lln(o(qqstvvxxzl{l}}TTȂȄ<<!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM5OM 5OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  YY)?*?44>!?!IIST^t^thhrTsT} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    ||b b""$H%H'').*.,,./11335m6m88:S;S==?5@5BBDEGGIIKjLjNNPLQLSSU.V.XXZ[]]__acbcddfEgEiik'l'nnp q szszuuw\x\zz|>}> ppPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]7 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1t  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)D*D44>(?(IIS T ^~^~hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00 x x""$`%`'')H*H,,.0/011346689;t;t==?X@XBBD[>]]_"`"bbdegxgxiik\l\nnp@q@ssu$v$xxz{}z}z^^ЄІ@@"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  \\)F*F44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// { {""$e%e'')O*O,,.9/9113#4#668 9 ;;==?l@lBBDVEVGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77}}gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM+OM+OMPMPMOEPMOEPMKPMKPMnPMpnPM!PM!PMϵPMϵPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1n  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ^^)P*P44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll^^ P P  BB44&&  " # %%'')u*u,,.g/g113Y4Y668K9K;;==>=@@B/C/EEG!H!JJLMOOQQStTtVVXbYb[[]P^P``b*?*IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUȉȋ;;!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM+OM+OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMϵPMϵPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f@  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ZZ)H*H44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llZZ H H  66$$ w w""$e%e'')S*S,,.A/A113/4/6689;;= > @@BBDpEpGGI\J\LLNFOFQQS0T0VVXY[[]^`y`ybbd_e_ggiEjElln)o)qqs t v|v|xxz^{^}}@@""ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM/OM /OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM%OM%OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMɵPMɵPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oG b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1g  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM)OM )OMOMOM]PM]PMDPMDPMuIPMuIPM/nPMp/nPMͮPMͮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  SS)=*=44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiSS = =  ''ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?K@KBBD5E5GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM)OM )OMOMOM]PM]PMDPMDPMiIPMiIPM/nPMp/nPMͮPMͮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPM{PM`{PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xP b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1b  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM#OM #OMOMOMWPMWPMDPMDPMiIPMiIPM)nPMp)nPMǮPMǮPM;PM;PMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 L} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 L} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 L  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xR b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xR b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xR b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM#OM #OMOMOMQPMQPMDPMDPMiIPMiIPM#nPMp#nPMPMPM;PM;PM-PM`-PMiQMiQM1QM1QMQML QMqRM qRMIRMp IRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations16  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>?IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMPMPMPM`PM PM PM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y% b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y% b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y% b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>(?(IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;= > @@BBDhEhGGIPJPLLN8O8QQS T VVXY[|[|]]_d`dbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMKPMKPMDPMDPMiIPMiIPMnPMpnPMPMPM;PM;PMKPM`KPMQMQM1QM1QMQML QM_RM _RM7RMp 7RMqSMt qSMTMT TMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations13S  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMPMPMPM`PM PM PM1QM1QMQML QMqRM qRMIRMp IRMSMt SM)TMT )TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?L@LBBD0E0GGIJLLNNPjQjSSUNVNXXZ2[2]]_`bbdegtgtiikXlXnnp%?%IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMPMPMPM`PM9QM9QM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b. b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1W   b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  RR)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``RR D D  66((   ""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMyOMyOMOM OMOMOMEPMEPMDPMDPM]IPM]IPMnPMpnPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SMMTMT MTMCRUMCRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 I} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 I} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 I  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL):*:44>"?"IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMPMPM'PM`'PMcQMcQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMyRUMyRUM!eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations13  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)D*D44>0?0IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OM=OM=OMOM|OM?OM?OMuOMuOMOM|OM5OMH5OMPMPMDPMPDPMJPMXJPMGMPMGMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PMPM| PMWPMXWPMQMQM-QM-QM@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``RR D D qq   ""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')u*u,,.a/a1134668 9 ;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWllnKoKqqs3t3vvxy{{}~ww__ӇӉGG//  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM=OM=OMOM|OM?OM?OMuOMuOMOM|OM5OMH5OMPMPMDPMPDPMJPMXJPMGMPMGMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PMPM| PM!PMX!PM]QM]QM-QM-QMX bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10`` NN)D*D44>2?2IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < < pp^^}}k k""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln3o3qqstvvxxzh{h}}JJ,,bb# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOM[OMl[OMOMOMOMOMPM@PMEPMEPM-LPM-LPMUPM@UPMXPM XPMnPMnPMQPMQPMPM PMPM PMPMd PMPM PMWPM WPMQMH QM-QMh-QM'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')S*S,,.;/;1~1~335f6f88:N;N==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II--  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMyOMyOMOMdOMaOMlaOMOMOM!OM!OMKPM@KPMDPMDPM3LPM3LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PMuPM uPMQMH QM-QMh-QM0?0IvIvST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``PP @ @  00   x x""$h%h'')X*X,,.H/H113848668(9(;;=>@@BCEEGGIpJpLLN\O\QQSHTHVVXY[z[z]]_f`fb c eegginjnllndodqqsPtPvvxp{h8`XPH@:4 . ( "   Hz4t bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIST^J^Jhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbd e g}g}iikclcnnpqssuuwrxrz{}}nnTTƉƋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMyOMyOMOMdOMaOMlaOMOMOM!OM!OMEPM@EPMDPMDPM3LPM3LPMUPM@UPMXPM XPMnPMnPMPMPMPM PMPM PMPMd PMPM PMKPM KPMQMH QM-QMh-QM$?$IgIgS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$J%J'')6*6,,."/"11346688:p;p==?\@\BBDHEHGGI4J4LLNOQQSTVGVGXXZ/[/]]_`bbd0e0ggijllnoq|q|ssudvdxxzL{L}}44xx``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM OM OMOMdOMaOMlaOMOMOM!OM!OMPM@PMyEPMyEPM3LPM3LPMUPM@UPMXPM XPMnPMnPMKPMKPMPM PMPM PMPMd PMPM PM]PM ]PMQMH QM-QMh-QMo?IISS];^;hhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__a[b[ddf=g=iikln_n_pprAsAuuw#x#zz|6}6jjڋڍJJ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM-QMP-QM)4QM,)4QMQMQMRM$RM[RM[RMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TM bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TM bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TM  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2Rj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1A~;   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)<*<44>*?*IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$Y%Y'')G*G,,.5/5113#4#6689;;==?v@vBBDdEdGGIRJRLLN'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMgOMTgOMOMOM'OM'OMKPM(KPMDPMDPM9LPM9LPMUPM(UPMXPMXPMnPMnPMPMPM PM  PMPM PMPML PM PM  PMcPM cPMQM0 QM-QMP-QM6QM,6QM?QM?QMqRM$qRMIRMIRMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UM bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UM bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UM  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 |Oo( b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1x5r/Q  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)7*744>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz``ӉӋFF,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMgOMTgOMOMOM'OM'OMPM(PMsEPMsEPM9LPM9LPMUPM(UPMXPMXPMnPMnPMEPMEPM PM  PMPM PMPML PM PM  PMcPM cPMQM0 QM-QMP-QM6QM,6QMՍQMՍQMqRM$qRMIRMIRMSMSMATMATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 JjRr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1c*q '  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>"?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMmOMTmOMOMOM-OM-OMQPM(QPMDPMDPM?LPM?LPMUPM(UPMXPMXPM#nPM#nPMPMPMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM)4QM,)4QMEQMEQMRM$RM[RM[RMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IO  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IO  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IO   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8X b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1DLP  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;=>@@BBDjEjGGIRJRLLN:O:QQS"T"VVX Y [~[~]]_f`fbbdNeNggi6j6llnoqqstvzvzxxzb{b}}JJ22rr b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMgEPMgEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM9PM9PM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM.QMP.QM)4QM,)4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x @ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1R$v P  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMmOMTmOMOMOM-OM-OMQPM(QPMDPMDPM?LPM?LPMUPM(UPMXPMXPM#nPM#nPMPMPMPM PMPM PMPML PMPM PMPM PMWQM0 WQM-QMP-QM6QM,6QMɍQMɍQMkRM$kRMCRMCRM}SM}SM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 HN bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 HN bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 HN  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 } * b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T\   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^t^thhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbddfngniikRlRnnp6q6ssuvxxzz|p}pTTƄƆ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMmEPMmEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM?PM?PM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM.QMP.QM6QM,6QMQMQMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 oTt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Hl>  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  MM)7*744>#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM#OML#OMOMTOMOMOMQOMQOMWPM(WPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM)nPM)nPMǮPMǮPM5PM 5PMPM PMPML PM7PM 7PMWPM WPMQM0 QM-QMP-QM)4QM,)4QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ie@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ie@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ie@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Om @  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)H*H44>:?:IIS&T&^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%{%{'')m*m,,._/_113Q4Q668C9C;;=5>5@@B'C'EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m o}o}qqsctcvvxIyI{{}/~/mmߌߎQQÑÓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMaEPMaEPMELPMELPMUPM(UPMYPMYPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM)4QM,)4QMQMQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 R" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 R" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 R"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {&F b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]:  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  ]])I*I44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii]] Q Q  EE99--!!  "#%%'(*w*w,,.c/c113O4O668;9;;;='>'@@BCEEGGIuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM#OML#OMOMTOMOMOMQOMQOMWPM(WPMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM)nPM)nPMǮPMǮPM5PM 5PMPM PMPML PM7PM 7PM!PM !PM]QM0 ]QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jd> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jd> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jd>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~ , b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1< Z)  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMgEPMgEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM9PM9PMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QM6QM,6QMUQMUQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 rVv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tQ. _ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMyRMyRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Dd b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Z4  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)D*D44>4?4IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln^o^qqsJtJvvx6y6{{}"~"pp\\ґғ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PM[EPM[EPMELPMELPMUPM(UPMYPMYPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMEPM EPMQM0 QM-QMP-QM/4QM,/4QMmQMmQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oI b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oI b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1oI  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hP8p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?O@OBBD5E5GGIJLLNOQtQtSSUZVZXXZ@[@]]_&`&bbd e ggiikelennpKqKssu1v1xxz{}}ppVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM6QM,6QMCQMCQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 . b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hBvJ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PM[EPM[EPMELPMELPMUPM(UPMYPMYPMnPMnPM-PM-PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQMkRM$kRMCRMCRM}SM}SMTMTMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Xx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 pXX } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  OO)5*544>?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM/OML/OMsOMTsOMOMOM3OM3OMcPM(cPMEPMEPMELPMELPMUPM(UPMYPMYPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM54QM,54QMaQMaQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1A bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1fK0a } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMUEPMUEPMELPMELPMUPM(UPMYPMYPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMmRMmRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d>   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jT> } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  VV)@*@44>+?+IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99)) u u""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33{{ee b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM/OML/OMsOMTsOMOMOM3OM3OMcPM(cPMEPMEPMELPMELPMUPM(UPMYPMYPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMkTMkTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 1 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1z_DF } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMUEPMUEPMELPMELPMUPM(UPMYPMYPMnPMnPM'PM'PMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM6QM,6QM9QM9QMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Zz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(|f:z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>&?&IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMߚOMߚOM}OML}OMyOMTyOMOMOM9OM9OMPM(PMIEPMIEPMKLPMKLPMUPM(UPM YPM YPM}nPM}nPMPMPMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM54QM,54QMEQMEQMRM$RMyRMyRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y3  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 |(H b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1uj_@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM5OML5OMyOMTyOMOMOM9OM9OMcPM(cPMEPMEPMKLPMKLPMUPM(UPM YPM YPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM6QM,6QMÐQMÐQMRM$RM[RM[RMSMSM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @N bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @N bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @N  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~5 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)<*<44>"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMߚOMߚOM}OML}OMyOMTyOMOMOM9OM9OMPM(PMOEPMOEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM!PM!PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RMgRMgRMSMSMqTMqTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1TI>35 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  QQ);*;44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`M?MIIS9T9^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1yykk ] ]  OOAA33%%  "#%%' ( **,,.t/t113f4f668X9X;;=J>J@@B@?@IIS(T(^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvjj ^ ^  RRFF::..  ""#"%%'(**,,.p/p113\4\668H9H;;=4>4@@B C EEG H JJLLNhOhQQSPTPVVX8Y8[[] ^ ``bce|e|ggidjdllnLoLqqs4t4vvxy{{}~xx``ԇԉHH00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMMOMMOMOM$OM{PM{PMEPMEPMuIPM$uIPMMnPMMnPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMRM RMSM SMTM TMwTUMwTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Jd b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Jd b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Jd b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Vv  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS'T'^^h i sysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdjejggiPjPlln4o4qqstvvxxzi{i}}KK--aa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMٚOMٚOMwOM wOMCOMCOMPMPMIEPMIEPMLPMLPM}nPMp}nPMPMPMPMPMPM`PM+PM+PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M) b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  ff)N*N44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvff V V  FF66&&  "#%z%z'')b*b,,.J/J1132426689;;=>@v@vBBD^E^GGIDJDLLN(O(QQS T V~V~XXZb[b]]_F`Fbbd*e*ggijllnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOM{PM{PMEPMEPMoIPMoIPMMnPMpMnPMPMPMAPMAPMuPM`uPMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Hh  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)U*U44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%}%}'')m*m,,.]/]113M4M668=9=;;=->-@@BCEEG H JJLLNoOoQQS[T[VVXGYG[[]3^3``bceeg h jjllnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ZZ)D*D44>*?*IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo[[ G G  33  i i""$S%S'')=*=,,.'/'11346688:p;p==?V@VBBD5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$]%]'')I*I,,.5/5113!4!668 9 ;;==?o@oBBD[E[GGIEJELLN-O-QQSTVVXXZq[q]]_Y`YbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMߚOMߚOM}OM }OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSUMSUMwfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V2 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1t  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ZZ)@*@44>"?"IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  }}c c""$I%I'')/*/,,./11335n6n88:T;T==?6@6BBDEGGIIKkLkNNPMQMSSU/V/XXZ[]]__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMAOM AOMOMOMuPMuPMEPMEPMuIPMuIPMGnPMpGnPMPMPMGPMGPMiPM`iPMQMQM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Cc  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS#T#^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbdhehggiRjRlln.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn^^ N N  >>.. z z""$d%d'')N*N,,.8/8113"4"668 9 ;;==?k@kBBDUEUGGI>J>LLN&O&QQSTVVXXZj[j]]_R`Rbbd:e:ggi"j"lln o q~q~ssufvfxxzN{N}}66||ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM;OM ;OMOMOMoPMoPM EPM EPMuIPMuIPMAnPMpAnPM߮PM߮PMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Vv  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)F*F44>.?.IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI2J2LLNOQQSSUqVqXXZW[W]]_=`=bbd#e#ggi j l|l|nnpbqbssuHvHxxz.{.}}mmSSƎƐ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM+OM+OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMϵPMϵPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_; b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  YY)C*C44>+?+IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  ~~h h""$R%R'')<*<,,.&/&11346688:o;o==?Y@YBBDCECGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggiikplpnnpTqTssu8v8xxz{}}rrVVɉɋ<<"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM;OM ;OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  aa)M*M44>5?5IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqee Y Y  MMAA11  " # %%'')k*k,,.W/W113C4C668/9/;;=>@@BCEuEuGGI]J]LLNEOEQQS-T-VVXY[[]]_q`qbbdYeYggiAjAlln)o)qqstvvxxzm{m}}UUɂɄ==""{{ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM+OM+OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMϵPMϵPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hB b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1o  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  XX)F*F44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjXX F F  44""u u""$c%c'')Q*Q,,.?/?113-4-6689;;= > @@BBDnEnGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SM;TMT ;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  [[)C*C44>'?'IIS T ^}^}hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// w w""$_%_'')G*G,,.///11346688:s;s==?W@WBBD;E;GGIJLLNOQuQuSSUYVYXXZ=[=]]_!`!bbdegwgwiik[l[nnp?q?ssu#v#xxz{}y}y]]τφ??!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM+OM+OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMϵPMϵPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hD b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  TT)>*>44>(?(IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjTT > >  ((qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLN O QQSSUiViXXZS[S]]_=`=bbd'e'ggijllnnpjqjssuNvNxxz2{2}}llމދPPސ44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM5OM 5OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  __)Q*Q44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm__ Q Q  CC55''  " # %%'')v*v,,.h/h113Z4Z668L9L;;=>>>@@B0C0EEG"H"JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qK b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qK b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qK b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJtJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM/OM /OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI8J8LLNOQQSTVrVrXXZV[V]]_:`:bbdeggijltltnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM)OM )OMOMOM]PM]PMDPMDPMiIPMiIPM/nPMp/nPMͮPMͮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1G} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1G} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1G  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMõPMõPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zT  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>?IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdegzgziik`l`nnpFqFssu,v,xxz{}}kkބކOO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM)OM )OMOMOM]PM]PMDPMDPMiIPMiIPM/nPMp/nPMͮPMͮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1H} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1H} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1H  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)?*?44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMõPMõPMPM`PMPMPM1QM1QMQML QMeRM eRM=RMp =RMwSMt wSMTMT TMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zV" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zV" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zV" b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]i^ihhrIsI} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3eeՋՍEE b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM#OM #OMOMOMWPMWPMDPMDPMiIPMiIPM)nPMp)nPMǮPMǮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]) b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>"?"IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI2J2LLNOQQSTVvVvXXZ^[^]]_F`Fbbd8e8ggi j llnoq|q|ssudvdxxzL{L}}44zzdd b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM#OM #OMOMOMQPMQPMDPMDPMiIPMiIPM#nPMp#nPMPMPM;PM;PMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>"?"IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMPMPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMQPMQPMDPMDPM]IPM]IPM#nPMp#nPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMEeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1D} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1D} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1D  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)C*C44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PM?QM?QM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM]eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1[  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  LL)D*D44>2?2IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMKPMKPMDPMDPM]IPM]IPMnPMpnPMPMPM/PM/PMPM`PMPMPM1QM1QMQML QMwRM wRMRMp RM}SMt }SM/TMT /TM%RUM%RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1E} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1E} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1E  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>?IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPM9PM`9PMuQMuQM1QM1QMQMT QMRM RMRMx RMSM| SMeTM\ eTM[RUM[RUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1G  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  HH):*:44>$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^HH 2 2  {{eeO O""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMCOMCOMOM|OMEOMEOM{OM{OMOM|OM;OMH;OMPMPMDPMPDPMJPMXJPMMMPMMMPMVPMPVPM ZPM ZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PM!PM| !PMQPMXQPMQMQM-QM-QM'+?+IIST^^his}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ? uuee  k k""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`ObbdCeCggi+j+llnoqqssuovoxxzW{W}}??''qq# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMaOMlaOMOMOM!OM!OMPM@PMEPMEPM3LPM3LPMUPM@UPMXPM XPMnPMnPMQPMQPMPM PMPM PMPMd PMPM PMKPM KPMQMH QM-QMh-QM.?.IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/91~1~335l6l88:Z;Z=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln=o=qqs't'vvxy{{}}ppZZχωDD..  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM=OM=OMOM|OMEOMEOM{OM{OMOM|OM;OMH;OMPMPMDPMPDPMJPMXJPMMMPMMMPMVPMPVPM ZPM ZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PM!PM| !PM3PMX3PMoQMoQM-QM-QM&?&IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7 z zffRRooY Y""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD%?%IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1  bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$N%N'')8*8,,."/"1d1d335N6N88:8;8==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpeqessuKvKxxz1{1}}ppVVɎɐ<<& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 ' bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMgOMlgOMOMOM'OM'OMKPM@KPMDPMDPM9LPM9LPMUPM@UPMXPM XPMnPMnPMPMPM PM  PMPM PMPMd PM PM  PMoPM oPMQMH QM-QMh-QM!+?+IpIpST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGISJSLLNAOAQQS/T/VtVtXXZb[b]]_P`Pbbdpepggi^j^llnQoQqqs5t5vvxy{{}}ooSSŇʼn77  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMgOMlgOMOMOM'OM'OMPM@PMyEPMyEPM9LPM9LPMUPM@UPMXPM XPMnPMnPMKPMKPM PM  PMPM PMPMd PM PM  PMuPM uPMQMH QM-QMh-QM,?,IIST^X^Xhhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN?IaIaS T ^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__II 3 3  ||ffP P""$:%:'')$*$,,./11335m6m88:W;W==?A@ABBD+E+GGIJLLNOQvQvSSU-V-XXZ[]]_`bbdeggijl}l}nnpiqissuMvMxxz1{1}}kk݉݋OO33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMgOMlgOMOMOM'OM'OMPM@PMEPMEPM9LPM9LPMUPM@UPMXPM XPMnPMnPMQPMQPM PM  PMPM PMPMd PM PM  PMEPM EPMQMH QM-QMh-QM??IIST^E^Ehhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbdegrgriikVlVnnpqsysyuuw]x]z{}t}tXXʄʆ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMPM PMQM0 QM.QMP.QM!9QM,!9QMQMQMRM$RM[RM[RMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TO bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TO bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TO  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 k&o b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1< bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1j'd!  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  WW)C*C44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33''  "#%%'')q*q,,.]/]113I4I668595;;=!>!@@B C EEGGIoJoLLNWOWQQS?T?VVX'Y'[[]^``bbdkekggiSjSlln;o;qqs#t#vvx y {{}}ggۂۄOOÇÉ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMmOMTmOMOMOM-OM-OMPM(PMsEPMsEPM?LPM?LPMUPM(UPMXPMXPMnPMnPMEPMEPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM?9QM,?9QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n:  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1X bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Z%p;  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMgOMTgOMOMOM'OM'OMQPM(QPMDPMDPM9LPM9LPMUPM(UPMXPMXPM#nPM#nPMPMPM PM  PMPM PMPML PM PM  PMiPM iPMQM0 QM-QMP-QM;QM,;QM;QM;QMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UO bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UO bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UO  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1y  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1^  X  I  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS);*;44>#?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$g%g'')O*O,,.7/711346689;{;{==?c@cBBDKEKGGI3J3LLNOQQSSUmVmXXZQ[Q]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM OM OMOMLOMmOMTmOMOMOM-OM-OMPM(PMyEPMyEPM?LPM?LPMUPM(UPMXPMXPMnPMnPMKPMKPMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM;QM,;QMCQMCQM}RM$}RMURMURMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Yy0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1  Q  g S } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PM'PM 'PMcQM0 cQM-QMP-QM39QM,39QMMQMMQMqRM$qRMIRMIRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 EQ  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 EQ  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 EQ   bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r2 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1H bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 f,rX  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  KK)5*544>?IIST^v^vhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?I@IBBD/E/GGIJLLNNPnQnSSUTVTXXZ:[:]]_ ` bbdegygyiik_l_nnpEqEssu+v+xxz{}}jj݄݆PP‰‹44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMmEPMmEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM?PM?PM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM.QMP.QMW9QM,W9QMsQMsQMRM$RMsRMsRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1,l bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations10X, | } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM;QM,;QMюQMюQM_RM$_RM7RM7RMqSMqSMTMTMSUMSUMYfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 DP bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 DP bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 DP  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 :Z b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18 ~ D  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]h^hhhrJsJ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__aWbWddf9g9iiklnnpprnsnuuwPxPzz|2}2ff֋֍FF b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMsEPMsEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMEPMEPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM .QMP .QM;QM,;QMQMQMRM$RM[RM[RMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .Nv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 T ( | P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM)OML)OMOMTOMOMOMQOMQOM]PM(]PMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM/nPM/nPMͮPMͮPM5PM 5PMPM PMPML PM7PM 7PM3PM 3PMoQM0 oQM-QMP-QMK9QM,K9QMQMQMRM$RM[RM[RMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ig@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ig@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ig@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u: b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1^ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xIk ^ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  PP):*:44>%?%IIS T ^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--uu__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMgEPMgEPMELPMELPMUPM(UPMYPMYPMnPMnPM9PM9PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QMo9QM,o9QM9QM9QMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 P" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 P" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 P"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1B bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1gF % B } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM)OML)OMOMTOMOMOMQOMQOM]PM(]PMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM/nPM/nPMͮPMͮPM5PM 5PMPM PMPML PM7PM 7PMWPM WPMQM0 QM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jf> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jf> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jf>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 @` b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 < ^ /  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>"?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMgEPMgEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM9PM9PMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM/OML/OMyOMTyOMOMOM9OM9OMcPM(cPMEPMEPMKLPMKLPMUPM(UPM YPM YPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QMc9QM,c9QMߏQMߏQMRM$RMgRMgRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @P bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @P bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @P  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations14t bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P, d $ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>/?/IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnKoKqqs/t/vvxy{{}}iiۂۄMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMaEPMaEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMmRMmRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1qM  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Vv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1X bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`J4  H } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)F*F44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::**  "#%x%x'')d*d,,.P/P113<4<668(9(;;=>@@BBDpEpGGIXJXLLN@O@QQS(T(VVXY[[]]_l`lbbdTeTggi#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMaEPMaEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMEPM EPMQM0 QM-QMP-QM3"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM5OML5OMyOMTyOMOMOM9OM9OMiPM(iPMEPMEPMKLPMKLPMUPM(UPM YPM YPM;nPM;nPMٮPMٮPMPM PMPM PMPML PMPM PMQPM QPMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @P bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @P bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @P  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .N b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1K bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1)w ^  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMUEPMUEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM'PM'PMPM PMPM PMPML PMPM PMoPM oPMQM0 QM-QMP-QM9QM,9QMёQMёQMRM$RMRMRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fB  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1n bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18- "   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PM[EPM[EPMKLPMKLPMUPM(UPM YPM YPMnPMnPM-PM-PMPM PMPM PMPML PMPM PM?PM ?PM{QM0 {QM-QMP-QMW2?2IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln'o'qqs t vzvzxxz\{\}}>> ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM;OML;OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM .QMP .QM9QM,9QMwQMwQMRM$RMaRMaRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @P bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @P bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @P  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4Tb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1` bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rd V p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMOEPMOEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM!PM!PM#PM #PMPM PMPML PM%PM %PM]PM ]PMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 O bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 O bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[7  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 O  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1    } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$r%r'')b*b,,.R/R113B4B668292;;=">"@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMUEPMUEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM'PM'PM#PM #PMPM PMPML PM%PM %PM-PM -PMiQM0 iQM-QMP-QM{,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88%%  ""$n%n'')X*X,,.B/B113,4,6689;;=>@u@uBBD_E_GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((pp b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMߚOMߚOM}OM }OMCOMCOMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMPMPMPM`PM+PM+PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>;?;IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIcJcLLNMOMQQS7T7VVX!Y![[] ^ ``bbdjejggiTjTlln>o>qqs(t(vvxy{{}}qq[[ЇЉEE// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMMOMMOMOM$OMPMPMEPMEPMuIPM$uIPMSnPMSnPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMsRM sRMSM SMqTM qTMATUMATUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fe b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fe b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Fe b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1]}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  aa)K*K44>3?3IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd"e"ggijlxlxnnp\q\ssu@v@xxz${$}}zz^^щыDD** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMߚOMߚOM}OM }OMCOMCOMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMPMPMPM`PM+PM+PM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)J*J44>2?2IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI6J6LLNOQQSTVuVuXXZ[[[]]_A`Abbd'e'ggi j llnnpfqfssuLvLxxz2{2}}qqWWʎʐ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMMOM MOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Qq  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>?>IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttbb P P  >>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIfJfLLNTOTQQSBTBVVX0Y0[[]^``b c eeggiqjqllnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)O*O44>7?7IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC33  " # %%'')m*m,,.Y/Y113E4E668191;;=>@@BCEwEwGGI_J_LLNGOGQQS/T/VVXY[[]]_s`sbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMGOM GOMOMOM{PM{PMEPMEPMoIPMoIPMMnPMpMnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1^~  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  \\)F*F44>0?0IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr\\ F F  00yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUqVqXXZ[[[]]_E`Ebbd/e/ggijllnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPMUEPMUEPMLPMLPMnPMpnPM'PM'PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X6 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)G*G44>+?+IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33 { {""$c%c'')K*K,,.3/311346689;w;w==?[@[BBD?E?GGI#J#LLNOQyQySSU]V]XXZA[A]]_%`%bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOMuPMuPMEPMEPMuIPMuIPMGnPMpGnPMPMPMGPMGPMuPM`uPMQMQM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Jj  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  hh)T*T44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD88,,  " # %%' ( **,,.n/n113Z4Z668F9F;;=2>2@@BCEEG H J~J~LLNfOfQQSNTNVVX6Y6[[]^``bcezezggibjbllnJoJqqs2t2vvxy{{}~vv^^҇҉FF.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM%OM%OMPMPMUEPMUEPMKPMKPMnPMpnPM'PM'PMɵPMɵPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1u  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  aa)S*S44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ooaa S S  EE77))  " # %%'')x*x,,.j/j113\4\668N9N;;=@>@@@B2C2EEG$H$JJLMOOQRTwTwVVXeYe[[]S^S``b?c?eeg)h)jjlmooqqsltlvvxRyR{{}8~8ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMAOM AOMOMOMuPMuPMEPMEPMuIPMuIPMGnPMpGnPMPMPMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1]}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)J*J44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%v%v'')^*^,,.F/F113.4.6689;;==?r@rBBDZEZGGI@J@LLN$O$QQSTVzVzXXZ^[^]]_B`Bbbd&e&ggi j l|l|nnp`q`ssuDvDxxz({(}} ~~bbԉԋFF** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM%OM%OMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMɵPMɵPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a?  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a?  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a?  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ]])K*K44>7?7IIST^^hisqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo]] K K  99'' z z""$h%h'')V*V,,.D/D113242668 9 ;;=>@@BBDsEsGGI_J_LLNIOIQQS3T3VVXY[[]^`|`|bbdbebggiHjHlln,o,qqstvvxxza{a}}CC%%wwYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1F} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1F} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1F  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  XX)B*B44>(?(IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?T@TBBD:E:GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikjljnnpPqPssu6v6xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jF b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1p  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)K*K44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++   ""$s%s'')c*c,,.S/S113C4C668393;;=#>#@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllncocqqsOtOvvx;y;{{}'~'uuaaבד b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM;OM ;OMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1G} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1G} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1G  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  VV)<*<44>?IIST^q^qhhrQsQ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11yy_ _""$E%E'')+*+,,./11335j6j88:P;P==?2@2BBDEGGIIKgLgNNPIQISSU+V+XXZ [ ]~]~__a`b`ddfBgBiik$l$nnpqswswuuwYxYzz|;};mm݋ݍMM b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jH b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //}}i i""$U%U'')A*A,,.-/-11346689;{;{==?g@gBBDSESGGI=J=LLN%O%QQS T VVXXZi[i]]_Q`Qbbd9e9ggi!j!lln o q}q}ssuevexxzM{M}}55yyaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  YY)C*C44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, x x""$b%b'')L*L,,.6/6113 4 668 9 ;;==?i@iBBDSESGGI/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM5OM 5OMOMOMcPMcPMEPMEPMuIPMuIPM5nPMp5nPMӮPMӮPMGPMGPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  UU)?*?44>'?'IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMPMPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)>*>44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM/OM /OMOMOMcPMcPMEPMEPMcIPMcIPM5nPMp5nPMӮPMӮPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1C} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1C} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1C  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM%OM%OMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMɵPMɵPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|X$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33qq b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM/OM /OMOMOM]PM]PMDPMDPMcIPMcIPM/nPMp/nPMͮPMͮPM5PM5PMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1D} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1D} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1D  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM%OM%OMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMɵPMɵPMPM`PMPMPM1QM1QMQML QMqRM qRMIRMp IRMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|Z& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|Z& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|Z& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>?IIST^u^uhhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM)OM )OMOMOM]PM]PMDPMDPMiIPMiIPM/nPMp/nPMͮPMͮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>2?2IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMO}O}QQSkTkVVXYYY[[]G^G``b3c3eeghjjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM#OM #OMOMOMWPMWPMDPMDPMiIPMiIPM)nPMp)nPMǮPMǮPM;PM;PMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)>*>44>$?$IIST^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdVeVggi?IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdeggiiklllnnpRqRssu8v8xxz{}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPM PM` PMEQMEQM1QM1QMQMT QMRM RMRMx RMSM| SM TM\  TMSUMSUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j6 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1`  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  OO)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //w w""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMQPMQPMDPMDPMWIPMWIPM#nPMp#nPMPMPM)PM: )PMPM* PMPM PM1QMr 1QMQMJ QMeRM" eRMRM RMkSM kSMTM TMQUMZ QUMdUMz } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1A} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1A} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-w* operation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z   reasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })zoutputElements*1152zinput0Elements241472zinput1Elements*9216binvocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1A  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)4*444>?IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMQPM`QPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM3eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1[  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  KK)?*?44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##qq] ]""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMCOMCOMOM|OMEOMEOM{OM{OMOM|OM;OMH;OMPMPMDPMPDPMJPMXJPMMMPMMMPMVPMPVPM ZPM ZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PM!PM| !PMKPMXKPMQMQM-QM-QMWz  X  6   r P ,lfD bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa QQ)G*G44>1?1IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I   ww!!   ""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdaeaggiIjIlln1o1qqstvvxy{u{u}}]]тфEE,,# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMgOMlgOMOMOM'OM'OMPM@PMEPMEPM9LPM9LPMUPM@UPMXPM XPMnPMnPMWPMWPM PM  PMPM PMPMd PM PM  PMcPM cPMQMH QM-QMh-QM ? IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss] ]""$%''))+r,r..01346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbdeggiiknlnnnpTqTssu:v:xxz { }}yy__щыCC''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMCOMCOMOM|OMEOMEOM{OM{OMOM|OM;OMH;OMPMPMDPMPDPMJPMXJPMMMPMMMPMVPMPVPM ZPM ZPMmPMmPMPM$ PMPM, PMPM PMPM$ PMPM PM!PM| !PMPMXPMQQMQQM-QM-QM#?#IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A ttdd  i i""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbd e ggiikclcnnpGqGssu+v+xxz{}}eeׄ׆II++ # b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMgOMlgOMOMOM'OM'OMPM@PMEPMEPM9LPM9LPMUPM@UPMXPM XPMnPMnPM]PM]PM PM  PMPM PMPMd PM PM  PM-PM -PMiQMH iQM-QMh-QM?IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qqW W""$%'{'{))+a,a..0|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##uuUUŐŒ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM#OMd#OMmOMlmOMOMOM-OM-OMQPM@QPMDPMDPM?LPM?LPMUPM@UPMXPM XPM#nPM#nPMPMPMPM PMPM PMPMd PMPM PMiPM iPMQMH QM-QMh-QM97?7IzIzS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaSS E E  77))   ""$x%x'')j*j,,.\/\113N4N668@9@;;=2>2@@B$C$EEGHJJLMO}O}QQSkTkVVX%Y%[[]^``b3c3eeghjjlmooqqsjtjvvxPyP{{}6~6ttXXʑʓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMmOMlmOMOMOM-OM-OMPM@PMEPMEPM?LPM?LPMUPM@UPMXPM XPMnPMnPMQPMQPMPM PMPM PMPMd PMPM PMPM PMQMH QM-QMh-QMu&?&IIST^P^Phhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd4e4ggijllnnpDqDssu,v,xxzH{H}}00xxbb  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMmOMlmOMOMOM-OM-OMQPM@QPMDPMDPM?LPM?LPMUPM@UPMXPM XPM#nPM#nPMPMPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM-+?+IkIkST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLN=O=QQS'T'VgVgXXZQ[Q]]_;`;bbdVeVggi!?!IIS T ^G^Ghhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikjljnnpqssuuwoxoz{}}llބކRRʼnŋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QM54QM,54QMύQMύQMRM$RMmRMmRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TQ" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TQ" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TQ"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 wt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]*w  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>1?1IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$i%i'')Y*Y,,.I/I113949668)9);;=>@@B C EEGGIqJqLLN]O]QQSITIVVX5Y5[[]!^!``b c eeggiojolln[o[qqsGtGvvx3y3{{}~ mmYYϑϓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM OM OMOMLOMsOMTsOMOMOM3OM3OMPM(PMyEPMyEPMELPMELPMUPM(UPMYPMYPMnPMnPMKPMKPMPM PMPM PMPML PMPM PMPM PMQM0 QM#.QMP#.QM#4QM,#4QMQMQMRM$RMaRMaRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q& bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q& bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q&  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Ka  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnLoLqqs0t0vvxy{{}}jj܂܄NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM#OML#OMmOMTmOMOMOM-OM-OMWPM(WPMDPMDPM?LPM?LPMUPM(UPMXPMXPM)nPM)nPMǮPMǮPMPM PMPM PMPML PMPM PMiPM iPMQM0 QM-QMP-QM6QM,6QM_QM_QM}RM$}RMURMURMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UQ" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UQ" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UQ"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 pQq0 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1D^+m  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)9*944>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$K%K'')7*7,,.#/#11346688:q;q==?]@]BBDIEIGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--qqYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMsOMTsOMOMOM3OM3OMPM(PMEPMEPMELPMELPMUPM(UPMYPMYPMnPMnPMQPMQPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QM6QM,6QM/QM/QMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 s1h b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1,wB ; {  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QM/4QM,/4QMQMQMRM$RMaRMaRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 AS$ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 AS$ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 AS$  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x o b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1G bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1V%t 7  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hhrtst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdZeZggiDjDlln.o.qqstvvxy{w{w}}aaւքKK55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMsEPMsEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMEPMEPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM#.QMP#.QM)4QM,)4QMGQMGQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q1 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q1  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1V,P  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGItJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMuPM uPMQM0 QM-QMP-QM6QM,6QM}QM}QMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u:Xx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Ca0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM/OML/OMOMTOM!OM!OMWOMWOMcPM(cPMEPMEPMiLPMiLPMUPM(UPM)YPM)YPM5nPM5nPMӮPMӮPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMWQM0 WQM-QMP-QM/4QM,/4QM;QM;QMRM$RMaRMaRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ii@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ii@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ii@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y# b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1S&y@  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)A*A44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$s%s'')_*_,,.K/K113747668#9#;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33ss b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMmEPMmEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM?PM?PMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM/4QM,/4QMQMQM}RM$}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q% bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q% bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\(  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q%  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1aB#@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM/OML/OMOMTOMOMOMQOMQOM]PM(]PMDPMDPMcLPMcLPMUPM(UPM#YPM#YPM/nPM/nPMͮPMͮPM5PM 5PMPM PMPML PM7PM 7PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QMˎQMˎQMwRM$wRMORMORMSMSM/TM/TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jh> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jh> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jh>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z$D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1LrE  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)9*944>?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMmEPMmEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM?PM?PMPM PMPM PMPML PMPM PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMQMQMkRM$kRMCRMCRM}SM}SMTMTMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q& bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q& bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`,  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q&  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t8 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1eF' } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf;?;IIS'T'^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeWW I I  ;;--  "#%|%|'')n*n,,.`/`113R4R668D9D;;=6>6@@B(C(EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m o~o~qqsdtdvvxJyJ{{}0~0nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMaEPMaEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM3PM3PMPM PMPM PMPML PMPM PMEPM EPMQM0 QM-QMP-QM/4QM,/4QMQMQMRM$RMgRMgRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sQ  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 (H b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lXD } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>*?*IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22zzdd b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM5OML5OMyOMTyOMOMOM9OM9OMcPM(cPMEPMEPMKLPMKLPMUPM(UPM YPM YPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMKPM KPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .N b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xV4 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMgEPMgEPMKLPMKLPMUPM(UPM YPM YPMnPMnPM9PM9PMPM PMPM PMPML PMPM PM9PM 9PMuQM0 uQM-QMP-QM6QM,6QMWQMWQMRM$RM[RM[RMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU!  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 w> b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations10t\ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM;OML;OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PM-PM -PMiQM0 iQM-QMP-QM54QM,54QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 { - b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1kT= } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>5?5IIS!T!^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjslln_o_qqsKtKvvx7y7{{}#~#qq]]ӑӓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PM[EPM[EPMQLPMQLPMUPM(UPMYPMYPMnPMnPM-PM-PM#PM #PMPM PMPML PM%PM %PM-PM -PMiQM0 iQM-QMP-QM54QM,54QMcQMcQMRM$RMsRMsRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hF  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 . b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1wne` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM5OML5OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PMWPM WPMQM0 QM-QMP-QM6QM,6QMKQMKQMRM$RMgRMgRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1&xaK } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)=*=44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMaEPMaEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM3PM3PM#PM #PMPM PMPML PM%PM %PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMkTMkTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q" bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q" bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q"  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r4 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1\SJAW } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>&?&IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnnphqhssuLvLxxz0{0}}jj܉܋NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PM!PM !PM]QM0 ]QM-QMP-QM;4QM,;4QMWQMWQMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1th\P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMUEPMUEPMWLPMWLPMUPM(UPMYPMYPMnPMnPM'PM'PM)PM )PMPM PMPML PM+PM +PMPM PMWQM0 WQM-QMP-QM;4QM,;4QMQMQMRM$RMyRMyRMSMSM݂TM݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1];  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ``)L*L44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<00$$  "#%%'(*z*z,,.f/f113R4R668>9>;;=*>*@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM;OML;OMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMKPM KPMQM0 QM-QMP-QM6QM,6QM QM QMRM$RMgRMgRMSMSMqTMqTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @R# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @R# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @R#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 {&F b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1PD8,D } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)<*<44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PM[EPM[EPMWLPMWLPMUPM(UPMYPMYPMnPMnPM-PM-PM)PM )PMPM PMPML PM+PM +PM'PM 'PMcQM0 cQM-QMP-QM6QM,6QMבQMבQMRM$RMaRMaRMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Q# bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Q# bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Q#  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 i" b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOMYOMOM$OMPMPM+EPM+EPMuIPM$uIPM_nPM_nPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMRM RMSM SM˂TM ˂TMTUMTUMCgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 Ai b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 Ai b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 Ai b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1]}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  jj)V*V44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ::&&  "#%%'')t*t,,.`/`113L4L668898;;=">"@@B C E~E~GGIfJfLLNNONQQS6T6VVXY[[]^`z`zbbdbebggiJjJlln2o2qqstvvxy{v{v}}^^҂҄FF++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMCOMCOMPMPMOEPMOEPMLPMLPMnPMpnPM!PM!PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ]])G*G44>-?-IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr^^ J J  66""  l l""$V%V'')@*@,,.*/*11346688:s;s==?Y@YBBD?E?GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz^^ЉЋBB&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMSOMSOMOM$OMPMPM%EPM%EPMuIPM$uIPMYnPMYnPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMmRM mRMSM SMSTM STM#TUM#TUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bg b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bg b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Bg b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1d  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  dd)L*L44>0?0IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88$$   ""$h%h'')P*P,,.8/8113 4 6689;|;|==?`@`BBDDEDGGI(J(LLN O Q~Q~SSUbVbXXZF[F]]_*`*bbdeggiikdldnnpHqHssu,v,xxz{}}ff؄؆HH**  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM=OM=OMPMPMUEPMUEPMLPMLPMnPMpnPM'PM'PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMaRMp aRMSMt SM TMT  TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ]])C*C44>%?%IIST^x^xhhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$  f f""$L%L'')2*2,,./11335q6q88:W;W==?9@9BBDEGGIIKnLnNNPPQPSSU2V2XXZ[]]__agbgddfIgIiik+l+nnp q s~s~uuw`x`zz|B}B$$ttTTĐĒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMSOM SOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Vv  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  hh)Z*Z44>J?JIIS6T6^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvhh Z Z  LL>>00""  "#%%'(**,,.q/q113c4c668U9U;;=G>G@@B9C9EEG+H+JJLMOOQRT~T~VVXlYl[[]Z^Z``bFcFeeg0h0jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPMUEPMUEPMLPMLPMnPMpnPM'PM'PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ^^)H*H44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11 } }""$g%g'')Q*Q,,.;/;113%4%6689;;==?n@nBBDXEXGGIAJALLN)O)QQSTVVXXZm[m]]_U`Ubbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMMOM MOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1e  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdgegggiMjMlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  \\)F*F44>.?.IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  k k""$U%U'')?*?,,.)/)11346688:r;r==?\@\BBDFEFGGI.J.LLNOQQSSUmVmXXZS[S]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOM MOMOMOM{PM{PMEPMEPMuIPMuIPMMnPMpMnPMPMPMGPMGPM{PM`{PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Qq  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)R*R44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%z%z'')j*j,,.Z/Z113J4J668:9:;;=*>*@@BCEEG H JJLLNlOlQQSXTXVVXDYD[[]0^0``bceeghj~j~llnjojqqsVtVvvxByB{{}.~.||hhޑޓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1v  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>7?7IIS%T%^^h i s{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI_J_LLNMOMQQS;T;VVX)Y)[[]^``bce|e|ggijjjllnSoSqqs7t7vvxy{{}}qqUULJlj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOM{PM{PMEPMEPM{IPM{IPMMnPMpMnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1d  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Z%Z'')F*F,,.2/21134668 9 ;;==?l@lBBDXEXGGIBJBLLN*O*QQSTVVXXZn[n]]_V`Vbbd>e>ggi&j&llnoqqssujvjxxzR{R}}::"" ~~ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPM[EPM[EPMKPMKPMnPMpnPM-PM-PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cC b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  WW)A*A44>+?+IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmWW A A  ++tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O QQSSUlVlXXZV[V]]_@`@bbd*e*ggijllnnpmqmssuQvQxxz5{5}}ooSSŎŐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMuPMuPMEPMEPMiIPMiIPMGnPMpGnPMPMPM;PM;PMoPM`oPMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1B} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1B} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1B  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Jj  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdeeeggiOjOlln9o9qqs#t#vvx y {{}}llVVˇˉ@@** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPMaEPMaEPMLPMLPMnPMpnPM3PM3PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lJ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  aa)M*M44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==11%%  "#%%'(*{*{,,.g/g113S4S668?9?;;=+>+@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1C} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1C} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1C  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1e  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)C*C44>+?+IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$V%V'')@*@,,.*/*11346688:s;s==?]@]BBDGEGGGI/J/LLNOQQSSUnVnXXZT[T]]_:`:bbd e ggijlylynnp_q_ssuEvExxz+{+}}jj݉݋PPÎÐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPMaEPMaEPMLPMLPMnPMpnPM3PM3PMյPMյPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lL b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  ]])E*E44>+?+IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==--   ""$q%q'')Y*Y,,.A/A113)4)6689;;==?m@mBBDUEUGGI;J;LLNOQQSTVuVuXXZY[Y]]_=`=bbd!e!ggijlwlwnnp[q[ssu?v?xxz#{#}}yy]]ωϋAA%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM;OM ;OMOMOMoPMoPM EPM EPMuIPMuIPMAnPMpAnPM߮PM߮PMGPMGPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ^^)J*J44>2?2IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>..  "#%|%|'')h*h,,.T/T113@4@668,9,;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uS b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uS b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uS b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>!?!IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM;OM ;OMOMOMiPMiPMEPMEPMuIPMuIPM;nPMp;nPMٮPMٮPMGPMGPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  XX)@*@44>$?$IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, t t""$\%\'')D*D,,.,/,11346688:p;p==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM5OM 5OMOMOMiPMiPMEPMEPMcIPMcIPM;nPMp;nPMٮPMٮPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM%OM%OMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMɵPMɵPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~\( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--ss]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM/OM /OMOMOMcPMcPMEPMEPMcIPMcIPM5nPMp5nPMӮPMӮPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM%OM%OMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMɵPMɵPMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~^* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM/OM /OMOMOMcPMcPMEPMEPMiIPMiIPM5nPMp5nPMӮPMӮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>4?4IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e1 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLNAOAQQS/T/VVXY[[] ^ ``bbdpepggi^j^llnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM)OM )OMOMOM]PM]PMDPMDPMiIPMiIPM/nPMp/nPMͮPMͮPM;PM;PMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>&?&IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>?IIS T ^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQvQvSSU`V`XXZJ[J]]_4`4bbdeggijl}l}nnpiqissuMvMxxz1{1}}kk݉݋OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM)OM )OMOMOMWPMWPMDPMDPMWIPMWIPM)nPMp)nPMǮPMǮPM)PM)PMPM`PMWQMWQM1QM1QMQMT QMRM RMRMx RMSM| SM˂TM\ ˂TMRUMRUMieUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1f#  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)@*@44>,?,IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM OM OMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PMWQMWQM1QM1QMQMT QMRM RMRMx RMSM| SMтTM\ тTMRUMRUMoeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1o#  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  UU)K*K44>5?5IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11%%  " # %%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOM#OM #OMOMOMWPMWPMDPMDPMWIPMWIPM)nPMp)nPMǮPMǮPM)PM)PMKPM`KPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMeTM\ eTM[RUM[RUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1R  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM);*;44>#?#IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM OM OMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMõPMõPMcPM`cPMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMYTM\ YTMORUMORUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1"o  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMIOMIOMOM|OMKOMKOMOMOM OM| OMAOMHAOMPMPMDPMPDPMJPMXJPMSMPMSMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM%PM %PMPM$ PMPM PM'PM| 'PMEPMXEPMQMQM-QM-QM$?$IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1]]II 5 5 u uaaMMwwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}ccՉՋGG++# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMmOMlmOMOMOM-OM-OMPM@PMEPMEPM?LPM?LPMUPM@UPMXPM XPMnPMnPM]PM]PMPM PMPM PMPMd PMPM PMiPM iPMQMH QM-QMh-QMi-?-IIS!T!^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$?%?'')+*+,,./113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbd]e]ggiEjElln-o-qqstvvxxzq{q}}YY͂̈́AA((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMCOMCOMOM|OMKOMKOMOMOM OM| OMAOMHAOMPMPMDPMPDPMJPMXJPMSMPMSMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM%PM %PMPM$ PMPM PM'PM| 'PMPMXPMKQMKQM-QM-QM=QM=QMqQM\qQMݔQMݔQM۟QM۟QMeRM8eRM=RM=RMwSMwSMSMSMTMlTMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 bWuoperation.0ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue4bytes2304patternContiguousinvocations1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1  bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1  bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r" b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1`.n <  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d 0@P`p ~  G *  8 Y F T=}bpP^, bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__ PP)6*644>?IIST^y^yhhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7 v vbbNNssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?.@.BBDEGGIIKcLcNNPEQESSU'V'XXZ [ ]z]z__ahbhddfJgJiik,l,nnpqssuuwaxazz|C}C%%wwWWǐǒ# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM!OM!OMOMdOMmOMlmOMOMOM-OM-OMPM@PMEPMEPM?LPM?LPMUPM@UPMXPM XPMnPMnPMcPMcPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QM!?!IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$ % '')*,|,|..01346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆGG))   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM#OMd#OMmOMlmOMOMOM-OM-OMWPM@WPMDPMDPM?LPM?LPMUPM@UPMXPM XPM)nPM)nPMǮPMǮPMPM PMPM PMPMd PMPM PMcPM cPMQMH QM-QMh-QMc"?"I`I`ST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``PP @ @  00    l l""$V%V'')@*@,,.*/*11346688:s;s==?]@]BBDGEGGGI2J2LLNOQQSTV@V@XXZ([(]]_`bbd8e8ggi j llnoq|q|ssudvdxxzL{L}}44||ff  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMmOMlmOMOMOM-OM-OMPM@PMEPMEPM?LPM?LPMUPM@UPMXPM XPMnPMnPMWPMWPMPM PMPM PMPMd PMPM PMPM PMQMH QM .QMh .QME;?;IIS'T'^f^fhiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeWW I I  ;;--  "#%|%|'')n*n,,.`/`113R4R668D9D;;=6>6@@B(C(EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m oJoJqqs0t0vvxy{{}2~2ppTTƑƓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM#OMd#OMmOMlmOMOMOM-OM-OMWPM@WPMDPMDPM?LPM?LPMUPM@UPMXPM XPM)nPM)nPMǮPMǮPMPM PMPM PMPMd PMPM PM9PM 9PMuQMH uQM-QMh-QM??I[I[S T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?K@KBBD5E5GGIJLLNOQxQxSSU'V'XXZ [ ]]__abdeggiiklllnnpPqPssu4v4xxz{}}nnTTljNj::   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMmOMlmOMOMOM-OM-OMPM@PMEPMEPM?LPM?LPMUPM@UPMXPM XPMnPMnPM]PM]PMPM PMPM PMPMd PMPM PMKPM KPMQMH QM-QMh-QM3 d 7 w  T  ] 1  0   V<| bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^S^Shhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>llnnp`q`ssuBvBxxz[{[}}==ssUU  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMPM PMQM0 QM.QMP.QMQ9QM,Q9QMQMQMRM$RM[RM[RMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TS& bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TS& bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TS&  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 o2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1(h bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1vC] 8 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)<*<44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$Y%Y'')G*G,,.5/5113#4#6689;;==?v@vBBDdEdGGITJTLLNBOBQQS0T0VVXY[[] ^ ``bbdqeqggi_j_llnHoHqqs,t,vvxy{{}}ff؂؄JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMEPMEPMKLPMKLPMUPM(UPM YPM YPMnPMnPMQPMQPMPM PMPM PMPML PMPM PMPM PMQM0 QM).QMP).QMi9QM,i9QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S* bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S* bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S*  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v/ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1fA w 4 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>5?5IIS!T!^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjslln_o_qqsKtKvvx7y7{{}#~#qq]]ӑӓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM)OML)OMsOMTsOMOMOM3OM3OM]PM(]PMDPMDPMELPMELPMUPM(UPMYPMYPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PMcPM cPMQM0 QM-QMP-QM;QM,;QMyQMyQMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 US& bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 US& bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 US&  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 tJj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 * w D   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)4*444> ? IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$;%;'')%*%,,./11335n6n88:X;X==?B@BBBD,E,GGIJLLNOQwQwSSUaVaXXZK[K]]_5`5bbdeggi j l~l~nnpbqbssuFvFxxz*{*}}dd։֋HH,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMyOMTyOMOMOM9OM9OMPM(PMEPMEPMKLPMKLPMUPM(UPM YPM YPMnPMnPMQPMQPMPM PMPM PMPML PMPM PMWPM WPMQM0 QM-QMP-QM'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$M%M'')9*9,,.%/%11346688:s;s==?_@_BBDKEKGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM/OML/OMyOMTyOMOMOM9OM9OMcPM(cPMEPMEPMKLPMKLPMUPM(UPM YPM YPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMPM PMQM0 QM .QMP .QMK9QM,K9QMQMQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @U( bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @U( bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @U(  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t:Z b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1#c bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1}Lj S } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  XX)D*D44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44((  "#%%'')r*r,,.^/^113J4J668696;;=">"@@BCEEGGIpJpLLNXOXQQS@T@VVX(Y([[]^``bbdlelggiTjTlln/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM/OML/OMyOMTyOMOMOM9OM9OM]PM(]PMDPMDPMKLPMKLPMUPM(UPM YPM YPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM{PM {PMQM0 QM-QMP-QM;QM,;QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @T' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @T' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @T'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 u]} b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 9  W &  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)<*<44>$?$IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpTqTssu8v8xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMyEPMyEPMWLPMWLPMUPM(UPMYPMYPMnPMnPMKPMKPM)PM )PMPM PMPML PM+PM +PM]PM ]PMQM0 QM-QMP-QM;QM,;QM]QM]QM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S6 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S6 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o;  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S6  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Hh b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations17  i B h } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}cc։֋II// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOM!OM!OMWOMWOMiPM(iPMEPMEPMiLPMiLPMUPM(UPM)YPM)YPM;nPM;nPMٮPMٮPM;PM ;PMſPM ſPMPML PM=PM =PMWPM WPMQM0 QM-QMP-QMW9QM,W9QMaQMaQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Ik@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Ik@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Ik@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <\ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1&f bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1mB f } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL)6*644>?IIST^w^whhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdegzgziik`l`nnpFqFssu,v,xxz{}}kkބކQQÉË55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMmEPMmEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM?PM?PM#PM #PMPM PMPML PM%PM %PM'PM 'PMcQM0 cQM-QMP-QM{9QM,{9QMQMQMRM$RMgRMgRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S) bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S) bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`,  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S)  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p/ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1J bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1( n Q  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)E*E44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii]] Q Q  EE99))  "#%w%w'')c*c,,.O/O113;4;668'9';;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbdSeSggi;j;lln#o#qqs t vvxxzg{g}}OOÂÄ77ww b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOMOMOMQOMQOMcPM(cPMEPMEPMcLPMcLPMUPM(UPM#YPM#YPM5nPM5nPMӮPMӮPM5PM 5PMPM PMPML PM7PM 7PM!PM !PM]QM0 ]QM-QMP-QM;QM,;QMQMQMeRM$eRM=RM=RMwSMwSMTMTMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jj> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jj> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jj>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v% b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 l A  k ; } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  LL)2*244>?IISS]i^ihhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ooU U""$;%;'')!*!,,./1z1z335`6`88:F;F==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3gg׋׍GG b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMsEPMsEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMEPMEPM#PM #PMPM PMPML PM%PM %PMiPM iPMQM0 QM-QMP-QM!?!IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM;OML;OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PM]PM ]PMQM0 QM-QMP-QMo9QM,o9QM-QM-QMRM$RMgRMgRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @T' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @T' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @T'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1<| bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pP0  ,l } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  QQ);*;44>&?&IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqvqvssu^v^xxzF{F}}..vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMgEPMgEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM9PM9PM#PM #PMPM PMPML PM%PM %PMPM PMWQM0 WQM-QMP-QM9QM,9QMMQMMQMRM$RMRMRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uU!  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 z b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1` bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1n\ J P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  [[)M*M44>???IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii[[ M M  ??11##  "#%%'')r*r,,.d/d113V4V668H9H;;=:>:@@B,C,EEGHJJLMOOQQSsTsVVXaYa[[]O^O``b;c;eeg%h%jjlmooqqshthvvxNyN{{}4~4rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM5OML5OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PM'PM 'PMcQM0 cQM-QMP-QM#?#IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikhlhnnpLqLssu0v0xxz{}}jj܄܆PPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMmEPMmEPMQLPMQLPMUPM(UPMYPMYPMnPMnPM?PM?PM#PM #PMPM PMPML PM%PM %PMcPM cPMQM0 QM-QMP-QM? } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  UU)C*C44>1?1IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM9QM,9QMQMQMRM$RMsRMsRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @T' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @T' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @T'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1R bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1J5 4 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnLoLqqs0t0vvxy{{}}jj܂܄NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMaEPMaEPMWLPMWLPMUPM(UPMYPMYPMnPMnPM3PM3PM)PM )PMPM PMPML PM+PM +PMPM PMQQM0 QQM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S& bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S& bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jJ  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S&  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 a b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1v bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1XQ J C V } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)I*I44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllncocqqsOtOvvx;y;{{}'~'uuaaבד b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOM;OML;OMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMPM PMWQM0 WQM-QMP-QM3$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMgEPMgEPMWLPMWLPMUPM(UPMYPMYPMnPMnPM9PM9PM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QMc+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33ww__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PM?PM ?PM{QM0 {QM-QMP-QM9QM,9QMQMQMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @T' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @T' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @T'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1h bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1    } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGItJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PM[EPM[EPM]LPM]LPMUPM(UPMYPMYPMnPMnPM-PM-PM/PM /PMPM PMPML PM1PM 1PM PM  PMEQM0 EQM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSM݂TM݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 S' bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 S' bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_?   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 S'  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Xx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations104 8 <  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>3?3IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbdbebggiLjLlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMPM PMKQM0 KQM-QMP-QMW(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$l%l'')T*T,,.>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMaEPMaEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM3PM3PM/PM /PMPM PMPML PM1PM 1PM?PM ?PM{QM0 {QM-QMP-QM*>44>(?(IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI,J,LLNOQQSSUkVkXXZQ[Q]]_7`7bbdeggijlvlvnnp\q\ssuBvBxxz({(}}ggډڋMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOM_OM_OMOM$OMPMPM+EPM+EPMuIPM$uIPM_nPM_nPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMyRM yRMSM SMqTM qTMATUMATUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 =k  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 =k  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 =k  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1d  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  aa)K*K44>1?1IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&p p""$Z%Z'')D*D,,../.11346689;w;w==?]@]BBDCECGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~bbԉԋFF** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMUEPMUEPMLPMLPMnPMpnPM'PM'PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  ff)R*R44>:?:IIS"T"^^h i s|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvjj ^ ^  RRFF66""  "#%%'')p*p,,.\/\113H4H668494;;=>@@BCEzEzGGIbJbLLNJOJQQS2T2VVXY[[]^`v`vbbd^e^ggiFjFlln.o.qqstvvxxzr{r}}ZZ΂΄BB''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMYOMYOMOM$OMPMPM+EPM+EPMuIPM$uIPM_nPM_nPMPMPMGPM$GPMPMPMQMQM1QM 1QMǀQM| ǀQMRM RMaRM aRMSM SM TM  TMSUMSUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 >i b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 >i b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1 >i b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1g  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  __)E*E44>'?'IIS T ^z^zhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&h h""$N%N'')4*4,,./11346s6s88:Y;Y==?;@;BBDEGGIIKpLpNNPRQRSSU4V4XXZ[]]__aibiddfKgKiik-l-nnpqssuuwbxbzz|D}D&&vvVVƐƒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMmRMp mRMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S5 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)J*J44>.?.IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvff V V  FF66""  ~ ~""$f%f'')N*N,,.6/611346689;z;z==?^@^BBDBEBGGI&J&LLN O Q|Q|SSU`V`XXZD[D]]_(`(bbd e g~g~iikblbnnpFqFssu*v*xxz{}}ddքֆFF((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOM YOMOMOMPMPM%EPM%EPMuIPMuIPMYnPMpYnPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1]}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  bb)L*L44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55""   ""$k%k'')U*U,,.?/?113)4)6689;;==?r@rBBD\E\GGIEJELLN-O-QQSTVVXXZq[q]]_Y`YbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%%mm b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMյPMյPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\< b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1x  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  dd)V*V44>F?FIIS2T2^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrdd V V  HH::,,  "#%%'(*{*{,,.m/m113_4_668Q9Q;;=C>C@@B5C5EEG'H'JJLMOOQRTzTzVVXhYh[[]V^V``bBcBeeg,h,jjlmooqqsotovvxUyU{{};~;!!ww[[͓͑ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMSOM SOMOMOMPMPM%EPM%EPMuIPMuIPMYnPMpYnPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMmRMp mRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1l  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ^^)H*H44>0?0IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##m m""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI0J0LLNOQQSSUoVoXXZU[U]]_;`;bbdeggijlulunnpYqYssu=v=xxz!{!}}ww[[Ή΋AA'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM1OM1OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMյPMյPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\>  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\>  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\>  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ``)N*N44>:?:IIS"T"^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr`` N N  <<** } }""$k%k'')Y*Y,,.G/G113545668#9#;;=>@@BBDvEvGGIbJbLLNLOLQQS6T6VVX Y [[] ^ ``bbdeeeggiKjKlln/o/qqstvvxxzd{d}}FF(( zz\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOM MOMOMOMPMPMEPMEPM{IPM{IPMSnPMpSnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>;?;IIS)T)^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIcJcLLNQOQQQS?T?VVX-Y-[[]^``b c eegginjnllnWoWqqs;t;vvxy{{}~uuYYˇˉ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eE b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ^^)N*N44>>..  ""$v%v'')f*f,,.V/V113F4F668696;;=&>&@@BCEEGHJ|J|LLNhOhQQSTTTVVX@Y@[[],^,``bceeghjzjzllnfofqqsRtRvvx>y>{{}*~*xxddڑړ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOM MOMOMOM{PM{PMEPMEPM{IPM{IPMMnPMpMnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  YY)C*C44>-?-IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ooYY C C  --vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLNOQQSSUnVnXXZX[X]]_B`Bbbd,e,ggijllnnpoqossuSvSxxz7{7}}qqUUǎǐ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMaEPMaEPMKPMKPMnPMpnPM3PM3PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eG b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ZZ)F*F44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  l l""$X%X'')D*D,,.0/011346689;~;~==?j@jBBDVEVGGI@J@LLN(O(QQSTVVXXZl[l]]_T`Tbbd;?;IIS#T#^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqee Y Y  MMAA55))  "#%%' ( **,,.k/k113W4W668C9C;;=/>/@@BCEEGHJ{J{LLNcOcQQSKTKVVX3Y3[[]^``bcewewggi_j_llnGoGqqs/t/vvxy{{}}ss[[χωCC++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM7OM7OMPMPMgEPMgEPM LPM LPMnPMpnPM9PM9PM۵PM۵PMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nN b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nN b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nN b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1l  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  XX)F*F44>2?2IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjXX F F  44""u u""$c%c'')Q*Q,,.?/?113-4-6689;;= > @@BBDnEnGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKlln5o5qqstvvx y {~{~}}hh݂݄RRLJlj<<&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOMuPMuPMEPMEPMiIPMiIPMGnPMpGnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1l  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  __)G*G44>-?-IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??//  ""$s%s'')[*[,,.C/C113+4+6689;;==?o@oBBDWEWGGI=J=LLN!O!QQSTVwVwXXZ[[[]]_?`?bbd#e#ggijlylynnp]q]ssuAvAxxz%{%}} {{__щыCC'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM7OM7OMPMPMgEPMgEPM LPM LPMnPMpnPM9PM9PM۵PM۵PMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nP b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nP b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nP b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  WW)A*A44>)?)IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //}}i i""$T%T'')>*>,,.(/(11346688:q;q==?[@[BBDEEEGGI-J-LLNOQQSSUlVlXXZR[R]]_8`8bbdeggijlwlwnnp]q]ssuCvCxxz){)}}hhۉۋNN44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMuPMuPMEPMEPMuIPMuIPMGnPMpGnPMPMPMGPMGPMPM`PM%PM%PM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  UU)?*?44>%?%IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?Q@QBBD7E7GGIJLLNOQvQvSSU\V\XXZB[B]]_(`(bbdeggiikglgnnpMqMssu3v3xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PM%PM%PM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wW# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wW# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wW# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)F*F44>.?.IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::**  "#%x%x'')d*d,,.P/P113<4<668(9(;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66tt b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM;OM ;OMOMOMoPMoPM EPM EPMuIPMuIPMAnPMpAnPM߮PM߮PMGPMGPMPM`PM%PM%PM1QM1QMQML QMqRM qRMIRMp IRMSMt SMTMT TMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  SS)9*944>?IISS]n^nhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..vv\ \""$B%B'')(*(,,./11335g6g88:M;M==?/@/BBDEGGIIKdLdNNPFQFSSU(V(XXZ [ ]{]{__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PM%PM%PM1QM1QMQML QM}RM }RMURMp URMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wY% b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wY% b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wY% b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)>*>44>"?"IIST^x^xhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**r r""$Z%Z'')B*B,,.*/*11346688:n;n==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM;OM ;OMOMOMoPMoPM EPM EPMcIPMcIPMAnPMpAnPM߮PM߮PM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  VV)@*@44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99)) u u""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM+OM+OMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>:?:IIS&T&^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffXX J J  <<..    "#%}%}'')o*o,,.a/a113S4S668E9E;;=7>7@@B)C)EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m o}o}qqsctcvvxIyI{{}/~/kk݌ݎOO b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM5OM 5OMOMOMiPMiPMEPMEPMcIPMcIPM;nPMp;nPMٮPMٮPM5PM5PMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>$?$IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::nnߎߐPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM5OM 5OMOMOMcPMcPMEPMEPMoIPMoIPM5nPMp5nPMӮPMӮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM OM OMOM OM OM OMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PMPMPM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR)B*B44>0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$j%j'')Z*Z,,.J/J113:4:668*9*;;=>@@B C EEGGIpJpLLN\O\QQSHTHVVX4Y4[[] ^ ``b c eegginjnllndodqqsPtPvvx!?!IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM OM OMOM OM OM OMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>$?$IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hbbd0e0ggijllnoq|q|ssudvdxxzL{L}}44xx`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM/OM /OMOMOM]PM]PMDPMDPM]IPM]IPM/nPMp/nPMͮPMͮPM/PM/PMPM`PMWQMWQM1QM1QMQMT QMRM RMRMx RMSM| SM˂TM\ ˂TMRUMRUMieUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1e$  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  YY)G*G44>1?1IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUllnIoIqqs1t1vvxy{{}~uu]]чщEE-- b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOM OM OMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMõPMõPMPM`PMWQMWQM1QM1QMQMT QMRM RMRMx RMSM| SMтTM\ тTMRUMRUMoeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1q%  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  LL)D*D44>0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln?o?qqs)t)vvxy{{}}rr\\чщFF00 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOM)OM )OMOMOM]PM]PMDPMDPM]IPM]IPM/nPMp/nPMͮPMͮPM/PM/PMEPM`EPMQMQM1QM1QMQMT QM}RM }RMRMx RMSM| SMYTM\ YTMORUMORUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1K  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)?*?44>%?%IIS T ^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpaqassuEvExxz){)}} ccՉՋGG++ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMõPMõPM{PM`{PMQMQM1QM1QMQMT QMRM RMRMx RMSM| SMeTM\ eTM[RUM[RUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations10  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  KK)=*=44>%?%IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##qq] ]""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpeqessuKvKxxz1{1}}ppVVɎɐ<< b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMIOMIOMOM|OMKOMKOMOMOM OM| OMAOMHAOMPMPMDPMPDPMJPMXJPMSMPMSMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM%PM %PMPM$ PMPM PM'PM| 'PMPMXPMKQMKQM-QM-QM92?2IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  ((CC1 1""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKllnAoAqqs+t+vvxy{{}}tt^^ӇӉHH22# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM!OM!OMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPMcPMcPMPM PMPM PMPMd PMPM PMuPM uPMQMH QM-QMh-QM?'?'IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$#%#'') * ,,..01346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;##mm  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMIOMIOMOM|OMKOMKOMOMOM OM| OMAOMHAOMPMPMDPMPDPMJPMXJPMSMPMSMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM%PM %PMPM$ PMPM PM'PM| 'PM3PMX3PMoQMoQM-QM-QM9'?'IIS T ^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##88$ $""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnpgqgssuMvMxxz3{3}}rrXXˎː>># b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM'OM'OMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPMiPMiPMPM PMPM PMPMd PMPM PMEPM EPMQMH QM-QMh-QM$?$IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$%''))+o,o..01346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggijlulunnpYqYssu=v=xxz!{!}}ww]]ЉЋCC))  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM)OMd)OMsOMlsOMOMOM3OM3OM]PM@]PMDPMDPMELPMELPMUPM@UPMYPM YPM/nPM/nPMͮPMͮPMPM PMPM PMPMd PMPM PM]PM ]PMQMH QM-QMh-QM*>44>(?(IdIdST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22""  ""$p%p'')\*\,,.H/H113444668 9 ;;= > @@BBDhEhGGIPJPLLN8O8QQS T V\V\XXZD[D]]_,`,bbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPM]PM]PMPM PMPM PMPMd PMPM PMPM PMQMH QM.QMh.QM?/?/IIST^Y^Yhisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnoqqssukvkxxz{}}kk݂݄OO33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM)OMd)OMsOMlsOMOMOM3OM3OM]PM@]PMDPMDPMELPMELPMUPM@UPMYPM YPM/nPM/nPMͮPMͮPMPM PMPM PMPMd PMPM PM?PM ?PM{QMH {QM-QMh-QMo0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1bDD  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dbD&jjLE. pP0   p  P  0  rpTT bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)6*644>?IUIUST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""j j""$R%R''):*:,,."/"113 4 6~6~88:f;f==?L@LBBD0E0GGIJLLNNPjQjSSUVXXZZ\k]k__abdegtgtiikXlXnnp>   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM!OM!OMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPM]PM]PMPM PMPM PMPMd PMPM PMoPM oPMQMH QM-QMh-QM?!?!IIS T ^H^Hhhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnp.q.ssuvxxz/{/}}iiۉۋMM11  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM/OML/OMyOMTyOMOMOM9OM9OMcPM(cPMEPMEPMKLPMKLPMUPM(UPM YPM YPM5nPM5nPMӮPMӮPMPM PMPM PMPML PMPM PMPM PMQM0 QM-QMP-QMA4QM,A4QMݎQMݎQMRM$RMmRMmRMSMSMTMTMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 TU* bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 TU* bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 TU*  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 s6h b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1\ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1yV3 , } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  TT)F*F44>8?8IIS$T$^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbTT F F  88**  "#%y%y'')k*k,,.]/]113O4O668A9A;;=3>3@@B%C%EEGHJJLMO~O~QQSlTlVVXZYZ[[]H^H``b4c4eeghjjlmo{o{qqsatavvxGyG{{}-~-kk݌ݎOO b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMEPMEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMWPMWPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM).QMP).QM54QM,54QMQMQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8X b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 L bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 gB  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM/OML/OMyOMTyOMOMOM9OM9OM]PM(]PMDPMDPMKLPMKLPMUPM(UPM YPM YPM/nPM/nPMͮPMͮPMPM PMPM PMPML PMPM PM]PM ]PMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM}TM}TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UU* bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UU* bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UU*  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Cc2R b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1mJ' } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbdWeWggi=j=lln!o!qqstvtvtxxzV{V}}88nnߎߐPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMEPMEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMWPMWPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM.QMP.QM6QM,6QMIQMIQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8Xz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xS. W } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)=*=44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM.QMP.QMA4QM,A4QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @W, bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @W, bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @W,  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x @y b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1S bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rQ0C } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  RR)B*B44>2?2IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$j%j'')Z*Z,,.J/J113:4:668*9*;;=>@@B C EEGGIrJrLLN^O^QQSJTJVVX6Y6[[]"^"``bceeggipjplln\o\qqsHtHvvx4y4{{} ~  nnZZБГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMyEPMyEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMKPMKPM/PM /PMPM PMPML PM1PM 1PMWPM WPMQM0 QM-QMP-QM)4QM,)4QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U9 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U9 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o;  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U9  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Z4  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOM OM OM?OM?OMcPM(cPMEPMEPMQLPMQLPMUPM(UPMYPMYPM5nPM5nPMӮPMӮPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1nM, } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN):*:44>&?&IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqvqvssu^v^xxzF{F}}..rrZZ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMEPMEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMQPMQPM/PM /PMPM PMPML PM1PM 1PMKPM KPMQM0 QM-QMP-QM6QM,6QM+QM+QMeRM$eRM=RM=RMwSMwSMTMTMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s?  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jDx4t } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM;OML;OMOMTOM!OM!OMWOMWOMiPM(iPMEPMEPMiLPMiLPMUPM(UPM)YPM)YPM;nPM;nPMٮPMٮPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM.QMP.QM;4QM,;4QMQMQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  ImB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  ImB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  ImB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }*Jr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 K bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 lM.[ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM OM OMOMLOMOMTOMOMOMEOMEOMPM(PMsEPMsEPMWLPMWLPMUPM(UPMYPMYPMnPMnPMEPMEPM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM/4QM,/4QM=QM=QMRM$RMgRMgRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U- bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U- bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U-  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1eJ/@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  TT)>*>44>)?)IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''s s""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOM!OM!OMWOMWOMiPM(iPMEPMEPMiLPMiLPMUPM(UPM)YPM)YPM;nPM;nPMٮPMٮPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JlA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JlA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JlA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 c6V b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pQ2 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM OM OMOMLOMOMTOMOMOMEOMEOMPM(PMyEPMyEPMWLPMWLPMUPM(UPMYPMYPMnPMnPMKPMKPM)PM )PMPM PMPML PM+PM +PMEPM EPMQM0 QM-QMP-QM6QM,6QMߏQMߏQM}RM$}RMURMURMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1y^C% } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMAOMLAOMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMgRMgRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 0P b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1eF'T } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN3?3IIS!T!^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGI[J[LLNIOIQQS7T7VVX%Y%[[]^``bcexexggifjfllnOoOqqs3t3vvxy{{}}mm߂߄QQÇÉ55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM;OML;OMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMEPM EPMQM0 QM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSM5TM5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 $D b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1iJ+ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMsEPMsEPMWLPMWLPMUPM(UPMYPMYPMnPMnPMEPMEPM)PM )PMPM PMPML PM+PM +PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMQMQMRM$RMaRMaRMSMSMkTMkTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y])  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 2 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  OO)9*944>%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMEPM EPMQM0 QM-QMP-QM54QM,54QMQMQMRM$RMRMRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y"B b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1iR; } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMgEPMgEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM9PM9PM/PM /PMPM PMPML PM1PM 1PM3PM 3PMoQM0 oQM-QMP-QM54QM,54QMQMQMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lN b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U* bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lN b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U* bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1lN  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U*  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r2 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1{vq } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PM3PM 3PMoQM0 oQM-QMP-QM6QM,6QMKQMKQMRM$RMgRMgRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 . b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$ v_I } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMmEPMmEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM?PM?PM/PM /PMPM PMPML PM1PM 1PMPM PMWQM0 WQM-QMP-QM6QM,6QM_QM_QMRM$RMaRMaRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U* bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U* bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U*  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lgb][ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>)?)IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpYqYssu=v=xxz!{!}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMGOMLGOMOMTOMOMOMKOMKOM{PM({PMEPMEPM]LPM]LPMUPM(UPMYPMYPMMnPMMnPMPMPM/PM /PMPM PMPML PM1PM 1PM9PM 9PMuQM0 uQM-QMP-QM;4QM,;4QMWQMWQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r4 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1th\P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMaEPMaEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM3PM3PM/PM /PMPM PMPML PM1PM 1PMPM PMQM0 QM5.QMP5.QM;4QM,;4QMYQMYQMRM$RMgRMgRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aC  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 g b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 P } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?Q@QBBD7E7GGIJLLNOQvQvSSU\V\XXZB[B]]_(`(bbdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMGOMLGOMOMTOMOMOMKOMKOM{PM({PMEPMEPM]LPM]LPMUPM(UPMYPMYPMMnPMMnPMPMPM/PM /PMPM PMPML PM1PM 1PM!PM !PM]QM0 ]QM-QMP-QM6QM,6QM QM QMRM$RMmRMmRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @V+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @V+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @V+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 t b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1PD8,D } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)>*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMaEPMaEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM3PM3PM/PM /PMPM PMPML PM1PM 1PMPM PMQM0 QM).QMP).QM6QM,6QMQMQMwRM$wRMORMORMSMSMTMTMSUMSUMwfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U+ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U+ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U+  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 g b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$*V } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  QQ)7*744>?IISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?/@/BBDEGGIIKdLdNNPFQFSSU(V(XXZ [ ]{]{__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMǚOMǚOMeOMeOMOM$OMPMPM1EPM1EPMuIPM$uIPMenPMenPMPMPMGPM$GPMPMPM7PM7PM1QM 1QMǀQM| ǀQMRM RMRM RMSM SMTM TMTUMTUMggUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations19m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdnenggiXjXllnBoBqqs,t,vvxy{{}~uu__ԇԉII33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U7 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  aa)K*K44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44!!   ""$j%j'')T*T,,.>/>113(4(6689;;==?q@qBBD[E[GGIDJDLLN,O,QQSTVVXXZp[p]]_X`Xbbd@e@ggi(j(llnoqqssulvlxxzT{T}}<<$$ ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOM_OM_OMOM$OMPMPM1EPM1EPMuIPM$uIPMenPMenPMPMPMGPM$GPMPMPM7PM7PM1QM 1QMǀQM| ǀQMRM RMRM RMSM SMTM TMYTUMYTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:k  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:k  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1:k  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)L*L44>4?4IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI8J8LLNOQQSTVwVwXXZ][]]]_C`Cbbd)e)ggijllnnphqhssuNvNxxz4{4}}ssYY̎̐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPM[EPM[EPMLPMLPMnPMpnPM-PM-PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1U9 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  __)I*I44>1?1IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI1J1LLNOQQSSUpVpXXZV[V]]_<`v>xxz"{"}}xx\\ωϋBB(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOM YOMOMOMPMPM+EPM+EPMuIPMuIPM_nPMp_nPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1d  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  gg)S*S44>;?;IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG77##  "#%%'')q*q,,.]/]113I4I668595;;=>@@BCE{E{GGIcJcLLNKOKQQS3T3VVXY[[]^`w`wbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM7OM7OMPMPMaEPMaEPM LPM LPMnPMpnPM3PM3PM۵PM۵PMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^@  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^@  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^@  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1u  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>:?:IIS(T(^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGIbJbLLNPOPQQS>T>VVX,Y,[[]^``bceeggimjmllnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOM YOMOMOMPMPM%EPM%EPMuIPMuIPMYnPMpYnPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMmRMp mRMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1o  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  aa)I*I44>-?-IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55!!  } }""$e%e'')M*M,,.5/511346689;y;y==?]@]BBDAEAGGI%J%LLN O Q{Q{SSU_V_XXZC[C]]_'`'bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM7OM7OMPMPMaEPMaEPM LPM LPMnPMpnPM3PM3PM۵PM۵PMPM`PMQMQM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^B b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^B b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^B b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ZZ)D*D44>.?.IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppZZ D D  ..wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBDG?GIIS3T3^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssee W W  II;;--  "#%%'(*|*|,,.n/n113`4`668R9R;;=D>D@@B6C6EEG(H(JJLMOOQRT{T{VVXiYi[[]W^W``bCcCeeg-h-jjlmooqqsptpvvxVyV{{}<~<""xx\\ΑΓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gI b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gI b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gI b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1n  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  dd)P*P44>:?:IIS"T"^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@44((  "#%%'(*~*~,,.j/j113V4V668B9B;;=.>.@@BCEEGHJzJzLLNbObQQSJTJVVX2Y2[[]^``bcevevggi^j^llnFoFqqs.t.vvxy{{}}rrZZ·ΉBB** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOMOMPMPMEPMEPM{IPM{IPMSnPMpSnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1r  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS!T!^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbddedggiJjJlln.o.qqstvvxxzc{c}}EE''yy[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMgEPMgEPMKPMKPMnPMpnPM9PM9PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gK b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gK b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gK b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)H*H44>.?.IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00    "#%t%t'')\*\,,.D/D113,4,6689;;==?p@pBBDXEXGGI>J>LLN"O"QQSTVxVxXXZ\[\]]_@`@bbd$e$ggijlzlznnp^q^ssuBvBxxz&{&}} ||``҉ҋDD(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOM MOMOMOMPMPMEPMEPMiIPMiIPMSnPMpSnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  __)O*O44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??//  ""$w%w'')g*g,,.W/W113G4G668797;;='>'@@BCEEGHJ}J}LLNiOiQQSUTUVVXAYA[[]-^-``bceeghj{j{llngogqqsStSvvx?y?{{}+~+yyeeۑۓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM7OM7OMPMPMmEPMmEPM LPM LPMnPMpnPM?PM?PM۵PM۵PMPM`PM+PM+PM1QM1QMQML QMRM RMaRMp aRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pR b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pR b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pR b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  TT)>*>44>$?$IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiUU A A  --yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMGOM GOMOMOM{PM{PMEPMEPMiIPMiIPMMnPMpMnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1s  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)E*E44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$W%W'')C*C,,.///11346689;};}==?i@iBBDUEUGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77{{cc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM7OM7OMPMPMmEPMmEPM LPM LPMnPMpnPM?PM?PM۵PM۵PMPM`PM+PM+PM1QM1QMQML QMwRM wRMORMp ORMSMt SMTMT TMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pT  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pT  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pT  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  TT):*:44>?IISS]o^ohhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //ww] ]""$C%C''))*),,./11335h6h88:N;N==?0@0BBDEGGIIKeLeNNPGQGSSU)V)XXZ [ ]|]|__a^b^ddf@g@iik"l"nnpqsusuuuwWxWzz|9}9kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMGOM GOMOMOM{PM{PMEPMEPM{IPM{IPMMnPMpMnPMPMPMMPMMPMuPM`uPMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Ss  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbdbebggiLjLlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMPMPMPM`PM%PM%PM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y[' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMuPMuPMEPMEPMuIPMuIPMGnPMpGnPMPMPMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1t  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)@*@44>(?(IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$S%S'')=*=,,.'/'11346688:p;p==?Z@ZBBDDEDGGI,J,LLNOQQSSUkVkXXZQ[Q]]_7`7bbdeggijlvlvnnp\q\ssuBvBxxz({(}}ggډڋMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PM%PM%PM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>%?%IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMAOM AOMOMOMoPMoPM EPM EPMcIPMcIPMAnPMpAnPM߮PM߮PM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>/?/IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbdSeSggi;j;lln#o#qqs t vvxxzg{g}}OOÂÄ77uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM OM OMOM OM+OM+OMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM;OM ;OMOMOMoPMoPM EPM EPMcIPMcIPMAnPMpAnPM߮PM߮PM5PM5PMPM`PMPMPM1QM1QMQML QMwRM wRMORMp ORMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  UU)=*=44>!?!IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM OM OMOM OM+OM+OMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMϵPMϵPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f2 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM;OM ;OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>;?;IIS'T'^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM OM OMOM OM OM OMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  XX)D*D44>.?.IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44((  "#%%'')r*r,,.^/^113J4J668696;;=">"@@BCEEGGInJnLLNVOVQQS>T>VVX&Y&[[]^``bbdjejggiRjRllnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM5OM 5OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o; b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)<*<44>"?"IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI2J2LLNOQQSSUlVlXXZP[P]]_4`4bbdeggiiknlnnnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM/OM /OMOMOMcPMcPMEPMEPM]IPM]IPM5nPMp5nPMӮPMӮPM/PM/PMPM`PMQQMQQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1\  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)E*E44>3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqllnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMõPMõPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMSTMT STMIRUMIRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10]]  RR)<*<44>"?"IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1]]II 5 5  !!  wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbdeggiikplpnnpVqVssu'?'IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM%OM%OMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMɵPMɵPMPM`PMPMPM1QM1QMQML QMkRM kRMRMp RMqSMt qSMTMT TMQUMQUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  PP)6*644>?IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMOOMOOMOM|OMQOMQOMOMOMOM|OMGOMHGOMPMPMDPMPDPM#JPMX#JPMYMPMYMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM+PM +PMPM$ PMPM PM-PM| -PMPMXPM3QM3QMu-QMu-QM?7?7IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11eeY Y""$%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnOoOqqs7t7vvxy{{}~{{ccׇ׉KK33# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM'OM'OMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPMiPMiPMPM PMPM PMPMd PMPM PMPM PMQMH QM-QMh-QM?7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsqtqvvxWyW{{}=~=## {{__ёѓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMIOMIOMOM|OMQOMQOMOMOMOM|OMGOMHGOMPMPMDPMPDPM#JPMX#JPMYMPMYMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM+PM +PMPM$ PMPM PM-PM| -PMPMXPMWQMWQM-QM-QM?)?)IIS T ^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!NN> >""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI9J9LLNOQQSTVsVsXXZW[W]]_;`;bbdeggijlulunnpeqessuIvIxxz-{-}}ggىًKK//# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM-OM-OMOMdOMsOMlsOMOMOM3OM3OMPM@PMEPMEPMELPMELPMUPM@UPMYPM YPMnPMnPMiPMiPMPM PMPM PMPMd PMPM PMQPM QPMQMH QM-QMh-QMu  ]   @J'g- bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)B*B44>0?0IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$$%$'')*,,./113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ~~``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM/OMd/OMyOMlyOMOMOM9OM9OMcPM@cPMEPMEPMKLPMKLPMUPM@UPM YPM  YPM5nPM5nPMӮPMӮPMPM PMPM PMPMd PMPM PMWPM WPMQMH QM-QMh-QM?ITITS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^JJ 6 6  ""nnX X""$B%B''),*,,,./11346u6u88:_;_==?G@GBBD-E-GGIJLLNNPlQlSSUVXXZZ\q]q__abdeggiikglgnnpMqMssu3v3xxz{}}rrXXʉʋ<<   b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM!OM!OMOMdOMyOMlyOMOMOM9OM9OMPM@PMEPMEPMKLPMKLPMUPM@UPM YPM  YPMnPMnPMcPMcPMPM PMPM PMPMd PMPM PMPM PMQMH QM#.QMh#.QME4?4IIS T ^^^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln&o&qqstvvxxz{}$~$rr^^ԑԓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM/OMd/OMyOMlyOMOMOM9OM9OM]PM@]PMDPMDPMKLPMKLPMUPM@UPM YPM  YPM/nPM/nPMͮPMͮPMPM PMPM PMPMd PMPM PM-PM -PMiQMH iQM-QMh-QM  )   g  B  j x U @-m0p bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  II)/*/44>?IIIISS]n^nhhrPsP} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$llR R""$8%8'')*,,./1w1w335]6]88:C;C==?'@'BBD E GzGzIIK\L\NNP>Q>SSUUWVXVZZ\8]8__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8ll܋܍LL  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM'OM'OMOMdOMyOMlyOMOMOM9OM9OMPM@PMEPMEPMKLPMKLPMUPM@UPM YPM  YPMnPMnPMcPMcPMPM PMPM PMPMd PMPM PM{PM {PMQMH QM-QMh-QME&?&IIST^K^Khhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$L%L'')8*8,,.$/$11346688:r;r==?^@^BBDJEJGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnnp?q?ssu'v'xxzJ{J}}22vv^^  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM5OML5OMOMTOM OM OM?OM?OMiPM(iPMEPMEPMQLPMQLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM#PM #PMPM PMPML PM%PM %PM{PM {PMQM0 QM-QMP-QM{9QM,{9QMQMQM}RM$}RMURMURMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UW. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UW. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UW.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 oa b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1T bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1_<  $d } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)8*844>#?#IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!m m""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI3J3LLNOQQSTVwVwXXZ_[_]]_G`Gbbd/e/ggijllnnpsqsssu[v[xxzC{C}}++ss]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOM OM OM?OM?OMPM(PMEPMEPMQLPMQLPMUPM(UPMYPMYPMnPMnPMWPMWPM#PM #PMPM PMPML PM%PM %PMPM PMQM0 QM/.QMP/.QMc9QM,c9QMQMQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W2 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W2 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W2  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 >^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations18x bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1N' Y  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM5OML5OMOMTOM OM OM?OM?OMcPM(cPMEPMEPMQLPMQLPMUPM(UPMYPMYPM5nPM5nPMӮPMӮPM#PM #PMPM PMPML PM%PM %PMWPM WPMQM0 QM-QMP-QM ? IIST^w^whhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikelennpIqIssu-v-xxz{}}ggلنMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOMOMLOMOMTOMOMOMEOMEOMPM(PMEPMEPMWLPMWLPMUPM(UPMYPMYPMnPMnPM]PM]PM)PM )PMPM PMPML PM+PM +PMPM PMQM0 QM.QMP.QM;QM,;QMWQMWQMwRM$wRMORMORMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 w )y b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations12 d = a } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)9*944>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM;OML;OMOMTOMOMOMEOMEOMiPM(iPMEPMEPMWLPMWLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM)PM )PMPM PMPML PM+PM +PMPM PMQM0 QM.QMP.QM{9QM,{9QM9QM9QMRM$RMaRMaRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Y0 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Y0 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Y0  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1O bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 hG & ? } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIUJULLNCOCQQS1T1VVXY[[] ^ ``bbdrerggi`j`llnIoIqqs-t-vvxy{{}}ggقلKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMQPMQPM5PM 5PMPM PMPML PM7PM 7PMKPM KPMQM0 QM-QMP-QMo9QM,o9QM'QM'QMRM$RMgRMgRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W= bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W= bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s?  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W=  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1^<  0p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM5OML5OMOMTOMOMOMEOMEOMiPM(iPMEPMEPMWLPMWLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM)PM )PMPM PMPML PM+PM +PM{PM {PMQM0 QM-QMP-QM!?!IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQxQxSSUbVbXXZL[L]]_6`6bbd e ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMWPMWPM5PM 5PMPM PMPML PM7PM 7PM!PM !PM]QM0 ]QM-QMP-QM  bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 r' b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1x V 4   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44> ? IIST^v^vhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?P@PBBD4E4GGIJLLNNPnQnSSURVRXXZ6[6]]_`bbddfpgpiikTlTnnp8q8ssuvxxz{}r}rVVȄȆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMAOMLAOMOMTOM'OM'OM]OM]OMoPM(oPM EPM EPMoLPMoLPMUPM(UPM/YPM/YPMAnPMAnPM߮PM߮PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM.QMP.QM{9QM,{9QMWQMWQMRM$RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IoF bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IoF bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IoF  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 q!w b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1K bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rS 4 [ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  YY)E*E44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%%'')s*s,,._/_113K4K668797;;=#>#@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM OM OMOMLOMOMTOMOMOMKOMKOMPM(PMyEPMyEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMKPMKPM/PM /PMPM PMPML PM1PM 1PM9PM 9PMuQM0 uQM-QMP-QM9QM,9QMQMQMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W1 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W1 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W1  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 : b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1V bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1XA*  6 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  ZZ)L*L44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhZZ L L  >>00""  "#%%'')q*q,,.c/c113U4U668G9G;;=9>9@@B+C+EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3qqUUǑǓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOM;OML;OMOMTOM'OM'OM]OM]OMoPM(oPM EPM EPMoLPMoLPMUPM(UPM/YPM/YPMAnPMAnPM߮PM߮PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM.QMP.QM%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$i%i'')Q*Q,,.9/9113!4!668 9 ;};}==?e@eBBDMEMGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMEPMEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMQPMQPM/PM /PMPM PMPML PM1PM 1PMPM PMKQM0 KQM-QMP-QM-0?0IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<rrTT b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMPM PMKQM0 KQM-QMP-QM{9QM,{9QMWQMWQMRM$RM[RM[RMSMSMSTMSTM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @X/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @X/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @X/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 h b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 kL - T } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbdeg{g{iikalannpGqGssu-v-xxz{}}ll߄߆RRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMsEPMsEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMEPMEPM/PM /PMPM PMPML PM1PM 1PM!PM !PM]QM0 ]QM-QMP-QM9QM,9QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y]) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1y])  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1l bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations10$   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>8?8IIS$T$^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJxJxLLNdOdQQSPTPVVX?IISS]j^jhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?+@+BBD E G~G~IIK`L`NNPBQBSSU$V$XXZ[]w]w__aYbYddf;g;iiklnnpprpspuuwRxRzz|4}4hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM OM OMOMLOMOMTOMOMOMKOMKOMPM(PMyEPMyEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMKPMKPM/PM /PMPM PMPML PM1PM 1PMPM PM9QM0 9QM{-QMP{-QMW*>44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$P%P'')<*<,,.(/(11346689;v;v==?b@bBBDNENGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PM?QM0 ?QM-QMP-QM9QM,9QMQMQMRM$RMmRMmRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @X/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @X/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @X/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]} b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1R bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1H3 2 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMmEPMmEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM?PM?PM/PM /PMPM PMPML PM1PM 1PM PM  PMEQM0 EQM-QMP-QM9QM,9QMQMQMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W. bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W. bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1nR  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W.  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 k b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1    } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbdaeaggiKjKlln5o5qqstvvx y {~{~}}hh݂݄RRLJlj<<&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PM9PM 9PMuQM0 uQM-QMP-QM3$?$IIS T ^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bbdeggiikilinnpMqMssu1v1xxz{}}kk݄݆QQĉċ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMmEPMmEPM]LPM]LPMUPM(UPMYPMYPMnPMnPM?PM?PM/PM /PMPM PMPML PM1PM 1PMPM PM'QM0 'QMi-QMPi-QM{'?'IIS T ^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggijlulunnp[q[ssuAvAxxz'{'}} ffىًLL22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMMOMLMOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMSnPMSnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PM3QM0 3QMu-QMPu-QM9QM,9QMQMQMRM$RMyRMyRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @X/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @X/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @X/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Rr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1h bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1    } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMgEPMgEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPM9PM9PM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM5.QMP5.QM9QM,9QM-QM-QMRM$RMyRMyRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 W/ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 W/ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1cG  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 W/  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1PX ` h $d } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<,,  "#%z%z'')f*f,,.R/R113>4>668*9*;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMMOMLMOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PM'PM 'PMcQM0 cQM-QMP-QM]%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeOO 9 9  ##  llV V""$@%@'')***,,./11335s6s88:];]==?G@GBBD1E1GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMgEPMgEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPM9PM9PM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM5.QMP5.QM*>44>$?$IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**r r""$Z%Z'')B*B,,.*/*11346688:n;n==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp>  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMǚOMǚOMeOMeOMOM$OMPMPM7EPM7EPM{IPM${IPMknPMknPM PM PMMPM$MPMPMPM7PM7PM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMTM TMTUMTUMggUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations15o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations15o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations15o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  nn)Z*Z44>D?DIIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ>>22  "&#&%%'(**,,.t/t113`4`668L9L;;=8>8@@B$C$EEGHJJLLNlOlQQSTTTVVXI?IIIS5T5^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uugg Y Y  KK==//!!  "#%%'(*~*~,,.p/p113b4b668T9T;;=F>F@@B8C8EEG*H*JJLMOOQRT}T}VVXkYk[[]Y^Y``bEcEeeg/h/jjlmooqqsrtrvvxXyX{{}>~>$$zz^^БГ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMǚOMǚOMeOMeOMOM$OMPMPM1EPM1EPM{IPM${IPMenPMenPMPMPMMPM$MPMPMPM7PM7PM2QM 2QM̀QM| ̀QMRM RMyRM yRMSM SMwTM wTMGTUMGTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations16m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)P*P44>6?6IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%|%|'')d*d,,.L/L1134446689;;=>@x@xBBD`E`GGIFJFLLN*O*QQSTVVXXZd[d]]_H`Hbbd,e,ggijllnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMaEPMaEPMLPMLPMnPMpnPM3PM3PMPMPMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W=  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W=  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1W=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  cc)Q*Q44>=?=IIS%T%^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uucc Q Q  ??--   ""$n%n'')\*\,,.J/J113848668&9&;;=>@@BCEyEyGGIeJeLLNOOOQQS9T9VVX#Y#[[] ^ ``bbdhehggiNjNlln2o2qqstvvxxzg{g}}II++ }}__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOM_OM _OMOMOMPMPM1EPM1EPMuIPMuIPMenPMpenPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1i  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ^^)H*H44>.?.IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##m m""$W%W'')A*A,,.+/+11346688:t;t==?Z@ZBBD@E@GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpVqVssu???IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11!!  "#%y%y'')i*i,,.Y/Y113I4I668999;;=)>)@@BCEEG H JJLLNkOkQQSWTWVVXCYC[[]/^/``bceeghj}j}llnioiqqsUtUvvxAyA{{}-~-{{ggݑݓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOM_OM _OMOMOMPMPM+EPM+EPMuIPMuIPM_nPMp_nPMPMPMGPMGPMPM`PMQMQM1QM1QMǀQML ǀQMRM RM[RMp [RMSMt SM TMT  TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1j  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  \\)B*B44>$?$IIST^w^whhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##  e e""$K%K'')1*1,,./11335p6p88:V;V==?8@8BBDEGGIIKmLmNNPOQOSSU1V1XXZ[]]__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##ssSSÐÒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM7OM7OMPMPMgEPMgEPM LPM LPMnPMpnPM9PM9PM۵PM۵PMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`F b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`F b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`F b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])I*I44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$[%['')G*G,,.3/31134668 9 ;;==?m@mBBDYEYGGICJCLLN+O+QQSTVVXXZo[o]]_W`Wbbd?e?ggi'j'llnoqqssukvkxxzS{S}};;## gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOM YOMOMOMPMPM+EPM+EPM{IPM{IPM_nPMp_nPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1f  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  __)I*I44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22  ~ ~""$h%h'')R*R,,.e>ggi&j&llnoqqssujvjxxzR{R}}::"" jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iM b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iM b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iM b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>5?5IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI]J]LLNGOGQQS1T1VVXY[[]^`z`zbbddedggiNjNlln8o8qqs"t"vvx y {{}}kkUUʇʉ??)) b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMSOM SOMOMOMPMPM%EPM%EPM{IPM{IPMYnPMpYnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1u  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>-?-IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?[@[BBDEEEGGI-J-LLNOQQSSUlVlXXZR[R]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXˉˋ>>$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMõPMõPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iO b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iO b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iO b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ZZ)D*D44>,?,IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  l l""$W%W'')A*A,,.+/+11346688:t;t==?^@^BBDHEHGGI0J0LLNOQQSSUoVoXXZU[U]]_;`;bbd!e!ggijlzlznnp`q`ssuFvFxxz,{,}}kkމދQQĎĐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOMOMPMPM%EPM%EPMoIPMoIPMYnPMpYnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1_  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>8?8IIS&T&^^h i s|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI`J`LLNNONQQS1?1IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==--  "#%{%{'')g*g,,.S/S113?4?668+9+;;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99ww b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMMOM MOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  VV)@*@44>*?*IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llVV @ @  **ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLN O QQSSUkVkXXZU[U]]_?`?bbd)e)ggijllnnplqlssuPvPxxz4{4}}nnRRĎĐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OM=OM=OMPMPMsEPMsEPMLPMLPMnPMpnPMEPMEPMPMPMPM`PM+PM+PM1QM1QMQML QMRM RM[RMp [RMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rX$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rX$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rX$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)A*A44>%?%IIS T ^{^{hhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==-- u u""$]%]'')E*E,,.-/-11346688:q;q==?U@UBBD9E9GGIJLLNOQsQsSSUWVWXXZ;[;]]_`bbdeguguiikYlYnnp=q=ssu!v!xxz{}w}w[[̈́͆== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOM{PM{PMEPMEPM{IPM{IPMMnPMpMnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1\|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>22&&  "#%%'(*|*|,,.h/h113T4T668@9@;;=,>,@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM OM OMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PM+PM+PM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{_+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  [[)M*M44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii[[ M M  ??11##  "#%%'')r*r,,.d/d113V4V668H9H;;=:>:@@B,C,EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMGOM GOMOMOM{PM{PMEPMEPM{IPM{IPMMnPMpMnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)D*D44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$p%p'')X*X,,.@/@113(4(6689;;==?l@lBBDTETGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM OM OMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PM+PM+PM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMGOM GOMOMOMuPMuPMEPMEPMcIPMcIPMGnPMpGnPMPMPM5PM5PMPM`PM%PM%PM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>"?"IIST^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM OM OMOM OM1OM1OMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMյPMյPMPM`PM%PM%PM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMAOM AOMOMOMuPMuPMEPMEPMcIPMcIPMGnPMpGnPMPMPM5PM5PMPM`PM%PM%PM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]k^khhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM;OM ;OMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMPM`PMPMPM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>&?&IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00vv`` b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMPMPMPM`PMPMPM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>)?)IIST^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGIQJQLLN;O;QQS%T%VVXY[[]]_n`nbbdXeXggiBjBlln6o6qqs t vvx y {{}}iiނބSSȇȉ=='' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOM;OM ;OMOMOMiPMiPMEPMEPMoIPMoIPM;nPMp;nPMٮPMٮPMAPMAPMPM`PMPMPM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikjljnnpNqNssu2v2xxz{}}llބކPPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMPMPMPM`PMPMPM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844> ? IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnVoVqqs:t:vvxy{{}~ttXXʇʉ<<  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM%OM%OMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMɵPMɵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMKeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)G*G44>/?/IIS#T#^^h i s}s}} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11!!   ""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDoEoGGIWJWLLN?O?QQS'T'VVXY[[]]_k`kbbd_e_ggiGjGlln/o/qqstvvxxzs{s}}[[ςτCC(( b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOM5OM 5OMOMOMcPMcPMEPMEPM]IPM]IPM5nPMp5nPMӮPMӮPM/PM/PM9PM`9PMuQMuQM1QM1QMQMT QMRM RMRMx RMSM| SMeTM\ eTM[RUM[RUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1z=  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)8*844>"?"IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnppqpssuTvTxxz8{8}}rrVVȎȐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM%OM%OMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMɵPMɵPMPM`PMPMPM1QM1QMQML QM}RM }RMRMp RMSMt SM5TMT 5TM+RUM+RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)=*=44>!?!IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!  i i""$Y%Y'')A*A,,.)/)11346688:m;m==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbd e g}g}iikalannpEqEssu)v)xxz { }}ccՄՆEE''  b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMOOMOOMOM|OMQOMQOMOMOMOM|OMGOMHGOM!PM!PMDPMPDPM#JPMX#JPMYMPMYMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM+PM +PMPM$ PMPM PM-PM| -PM3PMX3PMoQMoQM-QM-QMK9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //KK; ;""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllnoooqqs[t[vvxGyG{{}3~3 mm# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM-OM-OMOMdOMyOMlyOMOMOM9OM9OMPM@PMEPMEPMKLPMKLPMUPM@UPM YPM  YPMnPMnPMoPMoPMPM PMPM PMPMd PMPM PMPM PMQMH QM .QMh .QMK0?0IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$!%!'')*,,..013'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnXoXqqs>""  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMOOMOOMOM|OMQOMQOMOMOMOM|OMGOMHGOMPMPMDPMPDPM#JPMX#JPMYMPMYMPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM+PM +PMPM$ PMPM PM-PM| -PMPMXPM9QM9QM{-QM{-QMK+?+IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##44 ""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoqqssuovoxxzW{W}}??''kk# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM3OM3OMOMdOMyOMlyOMOMOM9OM9OMPM@PMEPMEPMKLPMKLPMUPM@UPM YPM  YPMnPMnPMoPMoPMPM PMPM PMPMd PMPM PM]PM ]PMQMH QM-QMh-QMK b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1Z4&f  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1dZ4hjD?xiR+]  6   h A   4 ;'g bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  JJ)8*844>$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``JJ 4 4  }}ggQ Q""$%'w'w))+a,a..01335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM5OMd5OMOMlOM OM OM?OM?OMiPM@iPMEPMEPMQLPMQLPMUPM@UPMYPM YPM;nPM;nPMٮPMٮPM#PM #PMPM PMPMd PM%PM %PM9PM 9PMuQMH uQM-QMh-QMQ)?)IISS]^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGIQJQLLN;O;QQS%T%VVXY[[]]_n`nbbdeggijl{l{n6o6qqs t vvx y {{}}iiނބSSȇȉ==''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM'OM'OMOMdOMOMlOM OM OM?OM?OMPM@PMEPMEPMQLPMQLPMUPM@UPMYPM YPMnPMnPMcPMcPM#PM #PMPM PMPMd PM%PM %PMPM PMQMH QM/.QMh/.QMQ2?2IIST^T^Thisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVllnoqxqxssu`v`xxz{}}llTTȇȉ<<$$  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM5OMd5OMOMlOM OM OM?OM?OMcPM@cPMEPMEPMQLPMQLPMUPM@UPMYPM YPM5nPM5nPMӮPMӮPM#PM #PMPM PMPMd PM%PM %PMPM PM?QMH ?QM-QMh-QMQ ? IISS]^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI$J$LLN O Q}Q}SSUcVcXXZI[I]]_/`/bebeddfKgKiik1l1nnp\q\ssuBvBxxz({(}}ggډڋMM33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM'OM'OMOMdOMOMlOM OM OM?OM?OMPM@PMEPMEPMQLPMQLPMUPM@UPMYPM YPMnPMnPMiPMiPM#PM #PMPM PMPMd PM%PM %PMPM PMQMH QM.QMh.QMQ$?$IIST^A^Ahhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$h%h'')P*P,,.8/8113 4 6689;|;|==?d@dBBDLELGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpqssuuwqxqz { }}vvZZ̉̋>>""  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM;OML;OMOMTOMOMOMEOMEOMiPM(iPMEPMEPMWLPMWLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM)PM )PMPM PMPML PM+PM +PMuPM uPMQM0 QM-QMP-QMA4QM,A4QM}QM}QMRM$RM[RM[RMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UY2 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UY2 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UY2  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Zz(H b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1V bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1mD  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)?*?44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33##  ""$q%q'')]*],,.I/I113545668!9!;;= > @@BBDiEiGGIQJQLLN9O9QQS!T!VVX Y [}[}]]_e`ebbdMeMggi5j5llnoqqstvyvyxxza{a}}II11qq b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM!OM!OMOMLOMOMTOMOMOMEOMEOMPM(PMEPMEPMWLPMWLPMUPM(UPMYPMYPMnPMnPM]PM]PM)PM )PMPM PMPML PM+PM +PMPM PMWQM0 WQM-QMP-QM/4QM,/4QMQMQMwRM$wRMORMORMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y}6 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y}6 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y}6  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v# b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]6  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOMOMOM5OML5OMOMTOMOMOMEOMEOMiPM(iPMEPMEPMWLPMWLPMUPM(UPMYPMYPM;nPM;nPMٮPMٮPM)PM )PMPM PMPML PM+PM +PMQPM QPMQM0 QM-QMP-QM6QM,6QMQMQMqRM$qRMIRMIRMSMSM)TM)TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 VY2 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 VY2 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 VY2  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 l5U b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1rI w] } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO)7*744>?IIST^s^shhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$S%S'');*;,,.#/#113 4 6688:g;g==?M@MBBD1E1GGIJLLNNPkQkSSUOVOXXZ3[3]]_`bbddfmgmiikQlQnnp5q5ssuvxxzz|o}oSSńņ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1lOM!OM!OMOMLOMOMTOMOMOMEOMEOMPM(PMEPMEPMWLPMWLPMUPM(UPMYPMYPMnPMnPMcPMcPM)PM )PMPM PMPML PM+PM +PM?PM ?PM{QM0 {QM-QMP-QM6QM,6QM%QM%QMeRM$eRM=RM=RMwSMwSMTMTMSUMSUM_fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y}7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y}7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y}7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 }*J b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hAs-m } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  LL)2*244>?IISS]i^ihhrKsK} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ooU U""$;%;'')!*!,,./1z1z335`6`88:F;F==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3gg׋׍GG b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMAOMLAOMOMTOMOMOMKOMKOMoPM(oPM EPM EPM]LPM]LPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM/PM /PMPM PMPML PM1PM 1PMPM PMQM0 QM.QMP.QM54QM,54QMSQMSQMRM$RMsRMsRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @[4 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @[4 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @[4  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 *Jy b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 I bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 ^3Y  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>9?9IIS%T%^^h i s~s~} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMOOQQSmTmVVX[Y[[[]I^I``b5c5eeghjjl m o|o|qqsbtbvvxHyH{{}.~.llތގPP‘“ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMWPMWPM;PM ;PMſPM ſPMPML PM=PM =PM PM  PMEQM0 EQM-QMP-QM/4QM,/4QMQMQMRM$RMaRMaRMSMSMTMTMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 YA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 YA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 YA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 i b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`@  0 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM;OML;OMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMuPM uPMQM0 QM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSMTMTMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 mXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]2\ . } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbdXeXggi>j>lln"o"qqstvuvuxxzW{W}}99ooQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPM]PM]PM;PM ;PMſPM ſPMPML PM=PM =PM9PM 9PMuQM0 uQM-QMP-QM6QM,6QMQMQM}RM$}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 YB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 YB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 YB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 x @ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`@  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>#?#IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikhlhnnpLqLssu0v0xxz{}}jj܄܆PPÉË66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMAOMLAOMOMTOM-OM-OMcOMcOMuPM(uPMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMGnPMGnPMPMPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM.QMP.QM/4QM,/4QM}QM}QMRM$RMyRMyRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Iq J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Iq J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Iq J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 8| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1W.  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS)C*C44>3?3IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$k%k'')[*[,,.K/K113;4;668+9+;;=>@@B C EEGGIsJsLLN_O_QQSKTKVVX7Y7[[]#^#``bceeggiqjqlln]o]qqsItIvvx5y5{{}!~! oo[[ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMKOMKOMPM(PMEPMEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMQPMQPM/PM /PMPM PMPML PM1PM 1PMPM PM3QM0 3QMu-QMPu-QM/4QM,/4QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y}5 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y}5 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y}5  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 \| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1kVA } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMAOMLAOMOMTOM-OM-OMcOMcOMuPM(uPMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMGnPMGnPMPMPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM .QMP .QM6QM,6QMQMQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jp I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jp I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jp I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 d m b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1\3 aW } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>'?'IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''uua a""$M%M'')9*9,,.%/%11346688:s;s==?_@_BBDKEKGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//ss[[ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMWPMWPM5PM 5PMPM PMPML PM7PM 7PM-PM -PMiQM0 iQM-QMP-QM6QM,6QMKQMKQMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y}6 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y}6 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p<  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y}6  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 o. b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1,mK } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  NN)8*844>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddNN 8 8  ""  kkU U""$?%?''))*),,./11335r6r88:\;\==?F@FBBD0E0GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM.QMP.QM54QM,54QM1QM1QMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 y"w b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1bD&0p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>-?-IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln0o0qqstvvxy{y{y}}cc؂؄MM‡‰77!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM OM OMOMLOMOMTOMOMOMQOMQOMPM(PMyEPMyEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMKPMKPM5PM 5PMPM PMPML PM7PM 7PMPM PM!QM0 !QMc-QMPc-QM54QM,54QMQQMQQMRM$RMsRMsRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{a-  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Oo b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1vlbP } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJvJvLLN^O^QQSFTFVVX.Y.[[]^``bbdrerggiZjZllnBoBqqs*t*vvxy{{}}nnVVʇʉ>>&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM.QMP.QM6QM,6QMӏQMӏQMRM$RMaRMaRMSMSMkTMkTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Yyl b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1jL. } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikrlrnnpXqXssu>v>xxz${$}} }}cc։֋II// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMyEPMyEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMKPMKPM5PM 5PMPM PMPML PM7PM 7PMPM PMWQM0 WQM-QMP-QM6QM,6QMQMQMRM$RM[RM[RMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1XND:F } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)@*@44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$l%l'')T*T,,.>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMMOMLMOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMSnPMSnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMKQM0 KQM-QMP-QM;4QM,;4QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 n  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1mZG  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMsEPMsEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMEPMEPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM).QMP).QM;4QM,;4QMQMQMRM$RMaRMaRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pV" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y2 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pV" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y2 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1pV"  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y2  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bb b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>$?$IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?P@PBBD6E6GGIJLLNOQuQuSSU[V[XXZA[A]]_'`'bbd e ggiikflfnnpLqLssu2v2xxz{}}qqWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMMOMLMOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PM'QM0 'QMi-QMPi-QM6QM,6QMQMQMRM$RM[RM[RMSMSM;TM;TM TUM TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Kk b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations14!{ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>!?!IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?Q@QBBD5E5GGIJLLNNPoQoSSUSVSXXZ7[7]]_`bbddfqgqiikUlUnnp9q9ssuvxxz{}s}sWWɄɆ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OM OM OMOMLOMOMTOMOMOMQOMQOMPM(PMsEPMsEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMEPMEPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM.QMP.QM6QM,6QMőQMőQMwRM$wRMORMORMSMSMTMTMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y~2 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y~2 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y~2  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ]} t b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  PP)6*644>?IISS]m^mhhrOsO} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++ssY Y""$?%?'')%*%,,. / 1~1~335d6d88:J;J==?.@.BBDEGGIIKcLcNNPEQESSU'V'XXZ [ ]z]z__a\b\ddf>g>iik l nnpqssssuuwUxUzz|7}7kkۋۍKK b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMSOMLSOMOMTOM!OM!OMWOMWOMPM(PM%EPM%EPMiLPMiLPMUPM(UPM)YPM)YPMYnPMYnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PM9QM0 9QM{-QMP{-QM;4QM,;4QMQMQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @Z3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @Z3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @Z3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 c b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xph } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMgEPMgEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPM9PM9PM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM5.QMP5.QM;4QM,;4QMQMQMRM$RMsRMsRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eK b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eK b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1eK  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 5U b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  WW)A*A44>,?,IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::** v v""$`%`'')J*J,,.4/411346689;};}==?g@gBBDQEQGGI1?1IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd\e\ggiBjBlln&o&qqstvyvyxxz[{[}}==ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMmEPMmEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPM?PM?PM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM5.QMP5.QM7QM,7QMaQMaQMRM$RMgRMgRMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 Y3 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 Y3 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 Y3  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Tt b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(2<FZ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  SS)=*=44>'?'IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,xxb b""$L%L'')6*6,,. / 113 4 6688:i;i==?S@SBBD=E=GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnTTljNj::  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM͚OM͚OMkOMkOMOM$OMPMPM=EPM=EPM{IPM${IPMqnPMqnPMPMPMMPM$MPMPMPM=PM=PM2QM 2QM̀QM| ̀QMRM RMRM RMSM SM1TM 1TMUUMUUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  hh)X*X44>F?FIIS2T2^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88((  "#%%'')p*p,,.`/`113P4P668@9@;;=0>0@@B C EEGHJJLLNrOrQQS^T^VVXJYJ[[]6^6``b"c"eeghjjllnpopqqs\t\vvxHyH{{}4~4  nn b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMgEPMgEPMLPMLPMnPMpnPM9PM9PMPMPMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y?  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y?  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Y?  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1t  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>=?=IIS+T+^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIeJeLLNSOSQQSATAVVX/Y/[[]^``b c eeggipjpllnYoYqqs=t=vvx!y!{{}~ww[[͇͉??## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM͚OM͚OMkOMkOMOM$OMPMPM7EPM7EPM{IPM${IPMknPMknPM PM PMMPM$MPMPMPM=PM=PM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMTM TMTUMTUM1gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  bb)N*N44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&t t""$`%`'')L*L,,.8/8113$4$6689;;==?r@rBBD^E^GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((ll b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMgEPMgEPMLPMLPMnPMpnPM9PM9PMPMPMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1YA  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1YA  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1YA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  ]])G*G44>1?1IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss]] G G  11zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUrVrXXZ\[\]]_F`Fbbd0e0ggijllnoqsqsssuWvWxxz;{;}}uuYYˎː== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMuIPMuIPMknPMpknPM PM PMGPMGPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdkekggiUjUlln?o?qqs)t)vvxy{{}}rr\\чщFF00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM=OM=OMPMPMmEPMmEPMLPMLPMnPMpnPM?PM?PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bH b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bH b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bH b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1o  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  gg)S*S44>=?=IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC77++  "#%%' ( **,,.m/m113Y4Y668E9E;;=1>1@@BCEEG H J}J}LLNeOeQQSMTMVVX5Y5[[]^``bceyeyggiajallnIoIqqs1t1vvxy{{}~uu]]чщEE-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOM_OM _OMOMOMPMPM1EPM1EPMuIPMuIPMenPMpenPMPMPMGPMGPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)I*I44>1?1IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI5J5LLNOQQSTVtVtXXZZ[Z]]_@`@bbd&e&ggi j llnnpeqessuKvKxxz1{1}}ppVVɎɐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OM=OM=OMPMPMmEPMmEPMLPMLPMnPMpnPM?PM?PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bJ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bJ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1bJ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1~  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)K*K44>1?1IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33##  "#%w%w'')_*_,,.G/G113/4/6689;;==?s@sBBD[E[GGIAJALLN%O%QQS T V{V{XXZ_[_]]_C`Cbbd'e'ggi j l}l}nnpaqassuEvExxz){)}} ccՉՋGG++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOM_OM _OMOMOMPMPM1EPM1EPM{IPM{IPMenPMpenPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)P*P44>8?8IIS T ^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD44   " # %%'')n*n,,.Z/Z113F4F668292;;=>@@BCExExGGI`J`LLNHOHQQS0T0VVXY[[]^`t`tbbd\e\ggiDjDlln,o,qqstvvxxzp{p}}XX̂̄@@%% ~~ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMmEPMmEPMKPMKPMnPMpnPM?PM?PMõPMõPMPM`PM1PM1PM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kQ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1}} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kQ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1}} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kQ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1}  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  WW)A*A44>'?'IIS T ^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llXX D D  00||f f""$P%P''):*:,,.$/$11346688:m;m==?S@SBBD9E9GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiikilinnpOqOssu5v5xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMYOM YOMOMOMPMPM+EPM+EPM{IPM{IPM_nPMp_nPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1p  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ^^)F*F44>*?*IIST^^hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22 z z""$b%b'')J*J,,.2/211346689;v;v==?Z@ZBBD>E>GGI"J"LLNOQxQxSSU\V\XXZ@[@]]_$`$bbdegzgziik^l^nnpBqBssu&v&xxz { }|}|``҄҆BB$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMõPMõPMPM`PM1PM1PM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSUMSUMwfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kS b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1}} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kS b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1}} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kS b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1}  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  WW)=*=44>?IIST^r^rhhrRsR} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22zz` `""$F%F''),*,,,./11335k6k88:Q;Q==?3@3BBDEGGIIKhLhNNPJQJSSU,V,XXZ[]]__aabaddfCgCiik%l%nnpqsxsxuuwZxZzz|<}<nnދލNN b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMOMOMPMPM%EPM%EPMoIPMoIPMYnPMpYnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1f  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  bb)T*T44>D?DIIS0T0^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppbb T T  FF88**  "#%%'(*y*y,,.k/k113]4]668O9O;;=A>A@@B3C3EEG%H%JJLMOOQRTxTxVVXfYf[[]T^T``b@c@eeg*h*jjlmooqqsmtmvvxSyS{{}9~9uuYYˑ˓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM OM OMOM OM=OM=OMPMPMsEPMsEPMLPMLPMnPMpnPMEPMEPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tZ& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tZ& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1tZ& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  XX)B*B44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++ w w""$a%a'')K*K,,.5/51134668 9 ;~;~==?h@hBBDRERGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33yycc b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOMOMPMPM%EPM%EPMoIPMoIPMYnPMpYnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1}  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIST^^hispsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdaeaggiGjGlln+o+qqs t v~v~xxz`{`}}BB$$vvXX b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM OM OMOM OM=OM=OMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t\( b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t\( b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t\( b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  VV)@*@44>(?(IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //{{e e""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI(J(LLNOQQSSUgVgXXZM[M]]_3`3bbdeggiikmlmnnpQqQssu5v5xxz{}}ooSSƉƋ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMSOM SOMOMOMPMPMEPMEPM{IPM{IPMSnPMpSnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  \\)L*L44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,,   ""$t%t'')d*d,,.T/T113D4D668494;;=$>$@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOMPMPMEPMEPM{IPM{IPMSnPMpSnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  VV)B*B44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..||h h""$T%T'')@*@,,.,/,11346689;z;z==?f@fBBDRERGGI%?%IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLNOQ|Q|SSUfVfXXZP[P]]_:`:bbd$e$ggijllnnpgqgssuKvKxxz/{/}}iiۉۋMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMGOM GOMOMOM{PM{PMEPMEPMcIPMcIPMMnPMpMnPMPMPM5PM5PM{PM`{PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1[{  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMյPMյPMPM`PM%PM%PM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIqJqLLNYOYQQSATAVVX)Y)[[]^``bbdmemggiUjUlln=o=qqs%t%vvx y {{}}ii݂݄QQŇʼn99!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMGOM GOMOMOMuPMuPMEPMEPMcIPMcIPMGnPMpGnPMPMPM5PM5PMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)=*=44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMյPMյPMPM`PM%PM%PM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n: b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>%?%IIS T ^{^{hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI5J5LLNOQQSSUoVoXXZS[S]]_7`7bbdeggiikqlqnnpUqUssu9v9xxz{}}ssWWɉɋ;; b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMAOM AOMOMOMuPMuPMEPMEPMoIPMoIPMGnPMpGnPMPMPMAPMAPMPM`PM%PM%PM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)D*D44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDlElGGITJTLLN?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?G@GBBD-E-GGIJLLNNPlQlSSURVRXXZ8[8]]_`bbdeggiikglgnnpMqMssu3v3xxz{}}rrVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMAOM AOMOMOMoPMoPM EPM EPMoIPMoIPMAnPMpAnPM߮PM߮PMAPMAPMPM`PM%PM%PM1QM1QMQML QMwRM wRMORMp ORMSMt SM/TMT /TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR):*:44>?IIST^x^xhhrZsZ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&n n""$V%V'')>*>,,.&/&11346688:j;j==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMPMPMPM`PMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1}} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1}} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1wC b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1}  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]n^nhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?'@'BBD E GzGzIIK\L\NNP>Q>SSU V XXZ[]s]s__a]b]ddf?g?iik!l!nnpqststuuwVxVzz|8}8jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17LOMOMOM;OM ;OMOMOMoPMoPM EPM EPM]IPM]IPMAnPMpAnPM߮PM߮PM/PM/PMPM`PMWQMWQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1S  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%}%}'')o*o,,.a/a113S4S668E9E;;=7>7@@B)C)EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m ooqqsotovvxUyU{{};~;!!ww[[͓͑ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM%OM%OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMɵPMɵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM9eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  LL)@*@44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //  k k""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`MbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%%mm b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOM5OM 5OMOMOMiPMiPMEPMEPM]IPM]IPM;nPMp;nPMٮPMٮPM/PM/PM3PM`3PMoQMoQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUM'eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1q6  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)B*B44>.?.IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln/o/qqstvvxxzd{d}}FF(( zz\\ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17LOMOMOMOM OM+OM+OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMSTMT STMIRUMIRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  JJ)<*<44>$?$IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBDA bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  )D*D44>4?4IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  ((==+ +""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjglln\o\qqs@t@vvx$y${{}~zz^^ЇЉBB&&# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM3OM3OMOMdOMOMlOM OM OM?OM?OMPM@PMEPMEPMQLPMQLPMUPM@UPMYPM YPMnPMnPMoPMoPM#PM #PMPM PMPMd PM%PM %PMPM PMQMH QM.QMh.QMQ5?5IIS!T!^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$/%/'')*,,./113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjsllnkokqqsWtWvvxCyC{{}/~/}}iiߑߓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMOOMOOMOM|OMWOMWOMOMOMOM|OMMOMHMOM!PM!PMDPMPDPM)JPMX)JPM_MPM_MPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM1PM 1PMPM$ PMPM PM3PM| 3PM-PMX-PMiQMiQM-QM-QMc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1`@) <|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d`@ `@ ^<  x \  V 7  4    m p P0,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^    ):*:44>&?&IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^HH 2 2  {{&& ""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnoqtqtssuXvXxxz<{<}} vvZZ̎̐>># b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM3OM3OMOMdOMOMlOM OM OM?OM?OMPM@PMEPMEPMQLPMQLPMUPM@UPMYPM YPMnPMnPMuPMuPM#PM #PMPM PMPMd PM%PM %PMiPM iPMQMH QM-QMh-QMQ)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$%''))+r,r..01346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM;OMd;OMOMlOMOMOMEOMEOMiPM@iPMEPMEPMWLPMWLPMUPM@UPMYPM YPM;nPM;nPMٮPMٮPM)PM )PMPM PMPMd PM+PM +PM-PM -PMiQMH iQM-QMh-QMW.?.IISS]^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbVV J J  >>22&&  "#%%'')p*p,,.\/\113H4H668494;;= > @@B C EEGGInJnLLNVOVQQS>T>VVX&Y&[[]^``bbd,e,ggijllnDoDqqs,t,vvxy{{}}ppXẊ̉@@((  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM-OM-OMOMdOMOMlOMOMOMEOMEOMPM@PMEPMEPMWLPMWLPMUPM@UPMYPM YPMnPMnPMiPMiPM)PM )PMPM PMPMd PM+PM +PMPM PMQMH QM/.QMh/.QMW-?-IIST^P^Phisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFllnnpiqissuSvSxxz{{{}}eeڂڄOOćĉ99##  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM5OMd5OMOMlOMOMOMEOMEOMiPM@iPMEPMEPMWLPMWLPMUPM@UPMYPM YPM;nPM;nPMٮPMٮPM)PM )PMPM PMPMd PM+PM +PM3PM 3PMoQMH oQM-QMh-QMW"?"IISS]^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22"" z z""$f%f'')N*N,,.6/611346689;z;z==?b@bBBDJEJGGI2J2LLNOQQSSUlVlXXZP[P]]_4`4bgbgddfKgKiik/l/nnpZqZssu>v>xxz"{"}}xx\\Ή΋@@$$  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM-OM-OMOMdOMOMlOMOMOMEOMEOMPM@PMEPMEPMWLPMWLPMUPM@UPMYPM YPMnPMnPMoPMoPM)PM )PMPM PMPMd PM+PM +PMPM PMQMH QM .QMh .QMW^ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1[6 ,l  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d[6lG"}X3i  D   l z 8 U  0  KxA bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844>"?"IIST^@^@hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD?IIST^u^uhhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##ooY Y""$C%C'')-*-,,./11346v6v88:`;`==?H@HBBD.E.GGIJLLNNPmQmSSUSVSXXZ9[9]]_`bbdegxgxiik^l^nnpDqDssu*v*xxz{}}ii܄܆OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM!OM!OMOMLOMOMTOMOMOMKOMKOMPM(PMEPMEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMcPMcPM/PM /PMPM PMPML PM1PM 1PM'PM 'PMcQM0 cQM-QMP-QM]9QM,]9QMQMQMRM$RMaRMaRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [{: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [{: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [{:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p0 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations12r bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1HvM  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDmEmGGIUJULLN=O=QQS%T%VVX Y [[]]_i`ibbdQeQggi9j9lln!o!qqs t v}v}xxze{e}}MM55uu b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOM;OML;OMOMTOMOMOMEOMEOMoPM(oPM EPM EPMWLPMWLPMUPM(UPMYPMYPMAnPMAnPM߮PM߮PM)PM )PMPM PMPML PM+PM +PMKPM KPMQM0 QM-QMP-QM?IISS]g^ghhrIsI} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%mmS S""$9%9'')*,,./1x1x335^6^88:D;D==?(@(BBD E G{G{IIK]L]NNP?Q?SSU!V!XXZ[]t]t__aVbVddf8g8iiklnnpprmsmuuwOxOzz|1}1eeՋՍEE b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM'OM'OMOMLOMOMTOMOMOMKOMKOMPM(PMEPMEPM]LPM]LPMUPM(UPMYPMYPMnPMnPMiPMiPM/PM /PMPM PMPML PM1PM 1PMKPM KPMQM0 QM-QMP-QM;QM,;QM?QM?QMqRM$qRMIRMIRMSMSM/TM/TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [{; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [{; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [{;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 4T b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$ { R ) I } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)9*944>?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMPM PMQM0 QM.QMP.QM]9QM,]9QMyQMyQMRM$RMaRMaRMSMSMTMTM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @]8 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @]8 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @]8  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~,Lr b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations11q bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1/Y.  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>$?$IIS T ^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hbbd0e0ggijllnoqtqtssu\v\xxzD{D}},,tt^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPM]PM]PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMWQM0 WQM-QMP-QMu9QM,u9QMuQMuQMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [E bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [E bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [E  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 g b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1H bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 d F x } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  YY)K*K44>=?=IIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggYY K K  ==//!!  "#%~%~'')p*p,,.b/b113T4T668F9F;;=8>8@@B*C*EEGHJJL M OOQQSqTqVVX_Y_[[]M^M``b9c9eeg#h#jjl m ooqqsftfvvxLyL{{}2~2ppTTƑƓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMoPM oPMQM0 QM-QMP-QM;QM,;QMQMQM}RM$}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @\7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1] b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @\7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @\7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Qq0 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 X -  V } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>!?!IIST^x^xhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,bbdeggiikflfnnpJqJssu.v.xxz{}}hhڄچNN44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM!OM!OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMcPMcPMAPM APM˿PM ˿PMPML PMCPM CPM9PM 9PMuQM0 uQM-QMP-QM b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1*  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 ( l N Z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMGOMLGOMOMTOM3OM3OMiOMiOM{PM({PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMMnPMMnPMPMPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM#.QMP#.QMc9QM,c9QMQMQMRM$RMmRMmRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IsN bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IsN bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IsN  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 w> b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1.n bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18jC  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)>*>44>.?.IIST^^hisrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$[%['')I*I,,.7/7113%4%6689;;=>@x@xBBDfEfGGIVJVLLNDODQQS2T2VVX Y [[]^``bbdsesggiajallnJoJqqs.t.vvxy{{}}hhڂڄLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMWPMWPM5PM 5PMPM PMPML PM7PM 7PM PM  PMEQM0 EQM-QMP-QM9QM,9QM;QM;QMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [{9 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [{9 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p<  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [{9  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1^ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xeR ? >~ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$o%o'')_*_,,.O/O113?4?668/9/;;=>@@BCEEGGIwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMGOMLGOMOMTOM3OM3OMiOMiOM{PM({PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMMnPMMnPMPMPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM.QMP.QM;QM,;QMEQMEQMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  Jr M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  Jr M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  Jr M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ur b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 u N ' G } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMWPMWPM5PM 5PMPM PMPML PM7PM 7PM!PM !PM]QM0 ]QM-QMP-QM?)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMMOMLMOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMSnPMSnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM#.QMP#.QM{9QM,{9QMuQMuQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @\7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @\7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @\7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p *| b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1D bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tX < t } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  ZZ)F*F44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66**  "#%%'')t*t,,.`/`113L4L668898;;=$>$@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln>o>qqs&t&vvxy{{}}jjނބRRƇƉ::"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMQPMQPM;PM ;PMſPM ſPMPML PM=PM =PMPM PM9QM0 9QM{-QMP{-QM9QM,9QMQMQMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}e1  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Uu b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1t bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1PH @ 8 D } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  UU)C*C44>1?1IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIYJYLLNCOCQQS-T-VVXY[[]^`v`vbbd`e`ggiJjJlln4o4qqstvvxy{}{}}}gg܂܄QQƇƉ;;%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMMOMLMOMOMTOM!OM!OMWOMWOM{PM({PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMMnPMMnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM.QMP.QM!*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMQPMQPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMKQM0 KQM-QMP-QMc&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMSOMLSOMOMTOM!OM!OMWOMWOMPM(PM%EPM%EPMiLPMiLPMUPM(UPM)YPM)YPMYnPMYnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PM!PM !PM]QM0 ]QM-QMP-QM9QM,9QMAQMAQMRM$RMaRMaRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @\7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @\7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @\7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 i b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hWF 5 :z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844> ? IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbd e g|g|iikblbnnpHqHssu.v.xxz{}}mmSSʼnŋ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OM OM OMOMLOMOMTOM!OM!OMWOMWOMPM(PMsEPMsEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMEPMEPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM5.QMP5.QM9QM,9QMӒQMӒQMRM$RMsRMsRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [}6 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [}6 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1rZ&  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [}6  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(+ . 1   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)G*G44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;++  "#%y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdUeUggi=j=lln%o%qqs t vvxxzi{i}}QQłń99 yy b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMSOMLSOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMSnPMSnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PM3QM0 3QMu-QMPu-QME?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf#?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))q q""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbdegsgsiikWlWnnp;q;ssuvxxz{}u}uYY˄ˆ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMYOMLYOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMKQM0 KQM-QMP-QM9QM,9QM QM QMRM$RMsRMsRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @\7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @\7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @\7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1p bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@: 4 . @ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  SS)=*=44>(?(IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&&r r""$\%\'')F*F,,.0/011346689;y;y==?c@cBBDMEMGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00xxbb b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMmEPMmEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPM?PM?PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM5.QMP5.QM9QM,9QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 [7 bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 [7 bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1gO  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 [7  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Cc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1   *  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  ]])O*O44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk]] O O  AA33%%  " # %%'')t*t,,.f/f113X4X668J9J;;=<><@@B.C.EEG H JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMSOMLSOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PM!QM0 !QMc-QMPc-QMi%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMsEPMsEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMEPMEPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM5.QMP5.QM3?3IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!uuWW b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMӚOMӚOMqOMqOMOM$OMPMPMCEPMCEPM{IPM${IPMwnPMwnPMPMPMMPM$MPMPMPM=PM=PM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMTM TMTUMTUM[gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>A?AIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIiJiLLNWOWQQSETEVVX3Y3[[]!^!``bceeggitjtlln]o]qqsAtAvvx%y%{{} ~ {{__чщCC'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMmEPMmEPMLPMLPMnPMpnPM?PM?PMPMPMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SM+TMT +TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[C b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[C b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[C b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  dd)T*T44>B?BIIS.T.^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttdd T T  DD44$$  "#%|%|'')l*l,,.\/\113L4L668<9<;;=,>,@@BCEEG H JJLLNnOnQQSZTZVVXFYF[[]2^2``bceeg h jjllnlolqqsXtXvvxDyD{{}0~0~~jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM͚OM͚OMkOMkOMOM$OMPMPM=EPM=EPM{IPM${IPMqnPMqnPMPMPMMPM$MPMPMPM=PM=PM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMTM TMYTUMYTUMgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  __)I*I44>3?3IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uu__ I I  33||f f""$P%P''):*:,,.$/$11346688:m;m==?W@WBBDAEAGGI+J+LLNOQQSSUtVtXXZ^[^]]_H`Hbbd2e2ggijllnoququssuYvYxxz={=}}!!ww[[͎͐?? b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMmEPMmEPMLPMLPMnPMpnPM?PM?PMPMPMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[E b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[E b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1[E b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)L*L44>6?6IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$^%^'')J*J,,.6/6113"4"6689;;==?p@pBBD\E\GGIFJFLLN.O.QQSTVVXXZr[r]]_Z`ZbbdBeBggi*j*llnoqqssunvnxxzV{V}}>>&&jj b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMuIPMuIPMqnPMpqnPMPMPMGPMGPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  kk)W*W44>A?AIIS)T)^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwkk _ _  SSGG;;//  "###%%'(**,,.q/q113]4]668I9I;;=5>5@@B!C!EEG H JJLLNiOiQQSQTQVVX9Y9[[]!^!``b c e}e}ggiejellnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMmEPMmEPMLPMLPMnPMpnPM?PM?PMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dL b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dL b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dL b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1l  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ^^)L*L44>8?8IIS"T"^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp^^ L L  ::(( { {""$i%i'')W*W,,.E/E113343668!9!;;=>@@BBDtEtGGI`J`LLNJOJQQS4T4VVXY[[]^`}`}bbdgegggiQjQlln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMuIPMuIPMknPMpknPM PM PMGPMGPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)M*M44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%y%y'')a*a,,.I/I1131416689;;=>@u@uBBD]E]GGICJCLLN'O'QQS T V}V}XXZa[a]]_E`Ebbd)e)ggi j llnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM=OM=OMPMPMsEPMsEPMLPMLPMnPMpnPMEPMEPMPMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dN b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dN b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1dN b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1{  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ]])G*G44>/?/IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  o o""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd$e$ggi j l}l}nnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM1EPM1EPM{IPM{IPMenPMpenPMPMPMMPMMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RMmRMp mRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1f  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  [[)E*E44>+?+IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    j j""$T%T'')>*>,,.(/(11346688:q;q==?W@WBBD=E=GGI#J#LLN O Q|Q|SSUbVbXXZH[H]]_.`.bbdeggiikmlmnnpSqSssu9v9xxz{}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM OM OMOM OMOMOMPMPMsEPMsEPMKPMKPMnPMpnPMEPMEPMPMPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mU! b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1{} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mU! b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1{} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mU! b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1{  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  ``)L*L44>4?4IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ppdd X X  LL@@00  "#%~%~'')j*j,,.V/V113B4B668.9.;;=>@@BCEtEtGGI\J\LLNDODQQS,T,VVXY[[]]_p`pbbdXeXggi@j@lln(o(qqstvvxxzl{l}}TTȂȄ<<!!zz b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOM_OM _OMOMOMPMPM1EPM1EPM{IPM{IPMenPMpenPMPMPMMPMMPMPM`PMQMQM1QM1QMǀQML ǀQMRM RM[RMp [RMSMt SMTMT TMSUMSUM}fUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  YY)?*?44>!?!IIST^t^thhrTsT} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    ||b b""$H%H'').*.,,./11335m6m88:S;S==?5@5BBDEGGIIKjLjNNPLQLSSU.V.XXZ[]]__acbcddfEgEiik'l'nnp q szszuuw\x\zz|>}> ppPP b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM OM OMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMgRMp gRMSMt SMGTMT GTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mW# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1{} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mW# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1{} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1mW# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1{  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)D*D44>(?(IIS T ^~^~hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp`` P P  @@00 x x""$`%`'')H*H,,.0/011346689;t;t==?X@XBBD[>]]_"`"bbdegxgxiik\l\nnp@q@ssu$v$xxz{}z}z^^ЄІ@@"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMOMOMPMPM+EPM+EPMoIPMoIPM_nPMp_nPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  \\)F*F44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// { {""$e%e'')O*O,,.9/9113#4#668 9 ;;==?l@lBBDVEVGGI?J?LLN'O'QQSTVVXXZk[k]]_S`Sbbd;e;ggi#j#lln o qqssugvgxxzO{O}}77}}gg b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM OM OMOM OMCOMCOMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v^* b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ^^)P*P44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll^^ P P  BB44&&  " # %%'')u*u,,.g/g113Y4Y668K9K;;==>=@@B/C/EEG!H!JJLMOOQQStTtVVXbYb[[]P^P``b*?*IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUȉȋ;;!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMCOMCOMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v`, b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v`, b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v`, b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ZZ)H*H44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1llZZ H H  66$$ w w""$e%e'')S*S,,.A/A113/4/6689;;= > @@BBDpEpGGI\J\LLNFOFQQS0T0VVXY[[]^`y`ybbd_e_ggiEjElln)o)qqs t v|v|xxz^{^}}@@""ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOMOMPMPM%EPM%EPM{IPM{IPMYnPMpYnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMRMp RMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1|} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1|} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g3 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1|  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  XX)H*H44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((  ""$p%p'')`*`,,.P/P113@4@668090;;= > @@BCEEGHJvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMSOM SOMOMOMPMPMEPMEPM{IPM{IPMSnPMpSnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  SS)=*=44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiSS = =  ''ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?K@KBBD5E5GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOMPMPMEPMEPMiIPMiIPMSnPMpSnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMтTMT тTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  __)K*K44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk__ S S  GG;;//##  "#%%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM7OM7OMPMPMEPMEPM LPM LPMnPMpnPMWPMWPM۵PM۵PMPM`PM+PM+PM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p< b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>,?,IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln/o/qqstvvxy{x{x}}bbׂׄLL66  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOM{PM{PMEPMEPMiIPMiIPMMnPMpMnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)A*A44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM7OM7OMPMPMEPMEPM LPM LPMnPMpnPMWPMWPM۵PM۵PMPM`PM+PM+PM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r> b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpWqWssu=v=xxz#{#}} ||bbՉՋHH.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMGOM GOMOMOM{PM{PMEPMEPMoIPMoIPMMnPMpMnPMPMPMAPMAPMPM`PM%PM%PM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>?IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMPMPMoPM`oPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yE b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1{} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yE b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1{} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1yE b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1{  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Mm  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>(?(IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;= > @@BBDhEhGGIPJPLLN8O8QQS T VVXY[|[|]]_d`dbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMAOM AOMOMOMuPMuPMEPMEPMoIPMoIPMGnPMpGnPMPMPMAPMAPMPM`PM%PM%PM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  MM)3*344>?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((ppV V""$<%<'')"*",,./1{1{335a6a88:G;G==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMPMPMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1{} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1{} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1{G b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1{  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1j  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?L@LBBD0E0GGIJLLNNPjQjSSUNVNXXZ2[2]]_`bbdegtgtiikXlXnnp%?%IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM!OM!OMOM OM+OM+OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1N b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  RR)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``RR D D  66((   ""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OMOMOM;OM ;OMOMOMoPMoPM EPM EPM]IPM]IPMAnPMpAnPM߮PM߮PM/PM/PM-PM`-PMiQMiQM1QM1QMQMT QMRM RMRMx RMSM| SMSTM\ STMIRUMIRUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1h/  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  LL):*:44>"?"IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qq[ [""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM!OM!OMOM OM+OM+OMPMPMEPMEPMKPMKPMnPMpnPMcPMcPMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM-eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1P b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)D*D44>0?0IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OMUOMUOMOM|OMWOMWOMOMOMOM|OMMOMHMOM'PM'PMDPMPDPM)JPMX)JPM_MPM_MPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM1PM 1PMPM$ PMPM PM3PM| 3PMPMXPM9QM9QM{-QM{-QM]@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``RR D D  66((SSE E""$%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b3?3IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55))  "#%I%I'')5*5,,.!/!113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWllnKoKqqs3t3vvxy{{}~ww__ӇӉGG//  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMUOMUOMOM|OMWOMWOMOMOMOM|OMMOMHMOM!PM!PMDPMPDPM)JPMX)JPM_MPM_MPMVPMPVPMZPMZPMmPMmPMPM$ PMPM, PM1PM 1PMPM$ PMPM PM3PM| 3PM-PMX-PMiQMiQM-QM-QM2?2IIST^^hiszsz} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **<<* *""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln3o3qqstvvxxzh{h}}JJ,,bb# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM9OM9OMOMdOMOMlOMOMOMEOMEOM PM@ PMEPMEPMWLPMWLPMUPM@UPMYPM YPMnPMnPM{PM{PM)PM )PMPM PMPMd PM+PM +PMuPM uPMQMH QM-QMh-QM]'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$*%*'')*,,..013#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II--  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMAOMdAOMOMlOMOMOMKOMKOMoPM@oPM EPM EPM]LPM]LPMUPM@UPMYPM YPMAnPMAnPM߮PM߮PM/PM /PMPM PMPMd PM1PM 1PMPM PM?QMH ?QM-QMh-QMc0?0IISS]^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``PP @ @  00   x x""$h%h'')X*X,,.H/H113848668(9(;;=>@@BCEEGGIpJpLLN\O\QQSHTHVVX4Y4[[] ^ ``bbdBeBggi.j.llndodqqsPtPvvx?IISS]z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?K@KBBD1E1GGIJLLNNPpQpSSUVVVXXZ<[<]]_"`"bWbWddf=g=iik#l#nnpIqIssu/v/xxz{}}nnTTƉƋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOM;OMd;OMOMlOMOMOMKOMKOMoPM@oPM EPM EPM]LPM]LPMUPM@UPMYPM YPMAnPMAnPM߮PM߮PM/PM /PMPM PMPMd PM1PM 1PM9PM 9PMuQMH uQM-QMh-QMc$?$IISS]^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$rr^ ^""$J%J'')6*6,,."/"11346688:p;p==?\@\BBDHEHGGI4J4LLNOQQSTVxVxXXZ`[`]]_H`Hb{b{ddfcgciikKlKnoq|q|ssudvdxxzL{L}}44xx``  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM3OM3OMOMdOMOMlOMOMOMKOMKOMPM@PMEPMEPM]LPM]LPMUPM@UPMYPM YPMnPMnPMuPMuPM/PM /PMPM PMPMd PM1PM 1PMPM PMQQMH QQM-QMh-QM?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__abddffhmimkkmnpqsrsruuwTxTzz|6}6jjڋڍJJ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMPM PMKQM0 KQM-QMP-QM/4QM,/4QMiQMiQMRM$RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U]: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U]: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U]:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 g b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1B bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1IWr  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  NN)<*<44>*?*IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``NN < <  **}}k k""$Y%Y'')G*G,,.5/5113#4#6689;;==?v@vBBDdEdGGIRJRLLN bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]y> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]y>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 : b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Y2   } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>'?'IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI7J7LLNOQQSTV{V{XXZc[c]]_K`Kbbd3e3ggijllnoqwqwssu_v_xxzG{G}}//wwaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMAOMLAOMOMTOMOMOMKOMKOMuPM(uPMEPMEPM]LPM]LPMUPM(UPMYPMYPMGnPMGnPMPMPM/PM /PMPM PMPML PM1PM 1PMEPM EPMQM0 QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 V]: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 V]: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 V]:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~,L b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1e,s 9  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)7*744>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz``ӉӋFF,, b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM-OM-OMOMLOMOMTOMOMOMQOMQOMPM(PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMnPMnPMoPMoPM5PM 5PMPM PMPML PM7PM 7PMPM PM9QM0 9QM{-QMP{-QM6QM,6QMQMQMwRM$wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]y? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]y? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]y?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 k b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d=oY } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>"?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM0 QM .QMP .QM/4QM,/4QM QM QMRM$RMaRMaRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @_< bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @_< bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @_<  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~k b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1P p P  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)@*@44>*?*IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddXX L L  @@44$$  ""$r%r'')^*^,,.J/J113646668"9";;=>@@BBDjEjGGIRJRLLN:O:QQS"T"VVX Y [~[~]]_f`fbbdNeNggi6j6llnoqqstvzvzxxzb{b}}JJ22rr b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM!OM!OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMcPMcPMAPM APM˿PM ˿PMPML PMCPM CPM!PM !PM]QM0 ]QM-QMP-QM/4QM,/4QM+QM+QMRM$RMmRMmRMSMSMTMTMTUMTUM7gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ] I bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ] I bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ] I  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 v$ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1dH,0p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIYJYLLNGOGQQS5T5VVX#Y#[[]^``bbdvevggidjdllnMoMqqs1t1vvxy{{}}kk݂݄OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMiPM iPMQM0 QM-QMP-QM6QM,6QMQMQMwRM$wRMORMORMSMSM/TM/TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 wJj8 b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@`0  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IIST^t^thhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bbddfngniikRlRnnp6q6ssuvxxzz|p}pTTƄƆ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM'OM'OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMcPMcPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PM!QM0 !QMc-QMPc-QM6QM,6QM͏QM͏QMRM$RM[RM[RMSMSMeTMeTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ] J bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ] J bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ] J  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ^~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tX< } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  MM)7*744>#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMMOMLMOMOMTOM9OM9OMoOMoOMPM(PMEPMEPMLPMLPM VPM( VPMAYPMAYPMSnPMSnPMPMPMSPM SPMݿPM ݿPMPML PMUPM UPMPM PMQM0 QM).QMP).QM54QM,54QMQMQMRM$RMyRMyRMSMSMTMTMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IuR bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IuR bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IuR  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Pp b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1[6  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  VV)H*H44>:?:IIS&T&^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddVV H H  ::,,  "#%{%{'')m*m,,._/_113Q4Q668C9C;;=5>5@@B'C'EEGHJJL M OOQQSnTnVVX\Y\[[]J^J``b6c6eeg h jjl m o}o}qqsctcvvxIyI{{}/~/mmߌߎQQÑÓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPM]PM]PM;PM ;PMſPM ſPMPML PM=PM =PMPM PMKQM0 KQM-QMP-QM54QM,54QMߏQMߏQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]y= bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]y= bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]y=  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 a b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1o^M  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  ]])I*I44>5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ii]] Q Q  EE99--!!  "#%%'(*w*w,,.c/c113O4O668;9;;;='>'@@BCEEGGIuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnAoAqqs)t)vvxy{{}}mmUUɇɉ==%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMMOMLMOMOMTOM3OM3OMiOMiOM{PM({PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMMnPMMnPMPMPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM.QMP.QM6QM,6QM[QM[QMRM$RMaRMaRMSMSMTMTMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JtQ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1` b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JtQ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JtQ  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 p&o b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1lG"}[ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM!OM!OMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPM]PM]PM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM]-QMP]-QM6QM,6QMQMQMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]y> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]y> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]y>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Qq b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1<+  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)?*?44>'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMSOMLSOMOMTOM!OM!OMWOMWOMPM(PM%EPM%EPMiLPMiLPMUPM(UPM)YPM)YPMYnPMYnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM).QMP).QM54QM,54QMsQMsQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ii b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1fL2p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  TT)D*D44>4?4IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$ | |""$l%l'')\*\,,.L/L113<4<668,9,;;=>@@B C EEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln^o^qqsJtJvvx6y6{{}"~"pp\\ґғ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMQPMQPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM#.QMP#.QM54QM,54QMQMQMRM$RMaRMaRMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i5  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ];  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 dz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1ztn } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>#?#IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?O@OBBD5E5GGIJLLNOQtQtSSUZVZXXZ@[@]]_&`&bbd e ggiikelennpKqKssu1v1xxz{}}ppVVȉȋ:: b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMSOMLSOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMSnPMSnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM.QMP.QM6QM,6QMQMQMRM$RMgRMgRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 iv b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1~dJV } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMWPMWPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM0 QM .QMP .QM6QM,6QMMQMMQMqRM$qRMIRMIRMSMSMTMTMSUMSUMqfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ];  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Dde b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hb\VJ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  OO)5*544>?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMYOMLYOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM#.QMP#.QM;4QM,;4QM'QM'QMRM$RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Bbz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1qbS ` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>.?.IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln1o1qqstvvxy{z{z}}ddقلNNÇÉ88"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMyEPMyEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMKPMKPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM5.QMP5.QM;4QM,;4QMGQMGQMRM$RMsRMsRMSMSMTMTMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t^* b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]{: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t^* b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]{: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t^*  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]{:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ww b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 @ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  VV)@*@44>+?+IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99)) u u""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`Obbd7e7ggijllnoq{q{ssucvcxxzK{K}}33{{ee b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMSOMLSOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM#.QMP#.QM6QM,6QMېQMېQMRM$RMgRMgRMSMSMqTMqTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 bw b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1D5& } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMQPMQPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM/.QMP/.QM6QM,6QM QM QMRM$RMgRMgRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]z: bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]z: bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ]z:  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 7W b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1#E } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  RR)<*<44>&?&IIS T ^}^}hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++wwa a""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88((  "#%v%v'')b*b,,.N/N113:4:668&9&;;=>@@BBDnEnGGIVJVLLN>O>QQS&T&VVXY[[]]_j`jbbdReRggi:j:lln"o"qqs t v~v~xxzf{f}}NN‚„66vv b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM-OM-OMcOMcOMPM(PMsEPMsEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMEPMEPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM5.QMP5.QMA4QM,A4QMQMQMRM$RMRMRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iS b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iS b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1iS  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ];  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Jj b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 00 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  WW)E*E44>5?5IIS#T#^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiWW E E  33!!t t""$b%b'')P*P,,.>/>113,4,6689;;=>@@BBDmEmGGI]J]LLNKOKQQS9T9VVX'Y'[[]^``bcezezggihjhllnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMYOMLYOMOMTOM-OM-OMcOMcOMPM(PM+EPM+EPMuLPMuLPMUPM(UPM5YPM5YPM_nPM_nPMPMPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PM9QM0 9QM{-QMP{-QM6QM,6QMQMQMRM$RMaRMaRMSMSMGTMGTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @^; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @^; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @^;  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 [{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1plhd } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)<*<44>"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OM OM OMOMLOMOMTOM-OM-OMcOMcOMPM(PMyEPMyEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMKPMKPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM5.QMP5.QM7QM,7QM͒QM͒QMRM$RMmRMmRMSMSMwTMwTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 ]; bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 ]; bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 ];  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 *J{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@P`p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  QQ);*;44>'?'IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggQQ ; ;  %%nnX X""$B%B''),*,,,./11346u6u88:_;_==?I@IBBD3E3GGIJLLN O Q~Q~SSUhVhXXZR[R]]_<`M?MIIS9T9^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1yykk ] ]  OOAA33%%  "#%%' ( **,,.t/t113f4f668X9X;;=J>J@@B@?@IIS(T(^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvjj ^ ^  RRFF::..  ""#"%%'(**,,.p/p113\4\668H9H;;=4>4@@B C EEG H JJLLNhOhQQSPTPVVX8Y8[[] ^ ``bce|e|ggidjdllnLoLqqs4t4vvxy{{}~xx``ԇԉHH00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMӚOMӚOMqOMqOMOM$OMPMPMCEPMCEPM{IPM${IPMwnPMwnPMPMPMMPM$MPMPMPMCPMCPM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMTM TM}TUM}TUM%gUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14s b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ww  ee)S*S44>???IIS'T'^^h i sysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1wwee S S  AA//   ""$p%p'')^*^,,.L/L113:4:668(9(;;=>@@BCE{E{GGIgJgLLNQOQQQS;T;VVX%Y%[[]^``bbdjejggiPjPlln4o4qqstvvxxzi{i}}KK--aa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OM7OM7OMPMPMsEPMsEPM LPM LPMnPMpnPMEPMEPM۵PM۵PMPM`PMQMQM2QM2QM̀QML ̀QMRM RMyRMp yRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]I b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]I b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1]I b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  ff)N*N44>4?4IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvff V V  FF66&&  "#%z%z'')b*b,,.J/J1132426689;;=>@v@vBBD^E^GGIDJDLLN(O(QQS T V~V~XXZb[b]]_F`Fbbd*e*ggijllnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMuIPMuIPMqnPMpqnPMPMPMGPMGPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SM+TMT +TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10uu  ee)U*U44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1uuee U U  EE55%%  "#%}%}'')m*m,,.]/]113M4M668=9=;;=->-@@BCEEG H JJLLNoOoQQS[T[VVXGYG[[]3^3``bceeg h jjllnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM OM OMOM OMCOMCOMPMPMsEPMsEPMLPMLPMnPMpnPMEPMEPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fP b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fP b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fP b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ZZ)D*D44>*?*IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo[[ G G  33  i i""$S%S'')=*=,,.'/'11346688:p;p==?V@VBBD5?5IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ss__ K K  77##q q""$]%]'')I*I,,.5/5113!4!668 9 ;;==?o@oBBD[E[GGIEJELLN-O-QQSTVVXXZq[q]]_Y`YbbdAeAggi)j)llnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM OM OMOM OMCOMCOMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMaRMp aRMSMt SM TMT  TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fR b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fR b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1fR b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ZZ)@*@44>"?"IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  }}c c""$I%I'')/*/,,./11335n6n88:T;T==?6@6BBDEGGIIKkLkNNPMQMSSU/V/XXZ[]]__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMOMOMPMPM7EPM7EPM{IPM{IPMknPMpknPM PM PMMPMMPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  __)M*M44>9?9IIS#T#^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq__ M M  ;;)) | |""$j%j'')X*X,,.F/F113444668"9";;=>@@BBDuEuGGIaJaLLNKOKQQS5T5VVXY[[] ^ `~`~bbdhehggiRjRlln.?.IIST^^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn^^ N N  >>.. z z""$d%d'')N*N,,.8/8113"4"668 9 ;;==?k@kBBDUEUGGI>J>LLN&O&QQSTVVXXZj[j]]_R`Rbbd:e:ggi"j"lln o q~q~ssufvfxxzN{N}}66||ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMIPMIPMknPMpknPM PM PMSPMSPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)F*F44>.?.IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI2J2LLNOQQSSUqVqXXZW[W]]_=`=bbd#e#ggi j l|l|nnpbqbssuHvHxxz.{.}}mmSSƎƐ99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMyEPMyEPMKPMKPMnPMpnPMKPMKPMPMPMPM`PM7PM7PM1QM1QMǀQML ǀQMRM RMmRMp mRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1y} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1y} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o[' b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1y  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  YY)C*C44>+?+IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnZZ F F  22  ~~h h""$R%R'')<*<,,.&/&11346688:o;o==?Y@YBBDCECGGI+J+LLNOQQSSUjVjXXZP[P]]_6`6bbdeggiikplpnnpTqTssu8v8xxz{}}rrVVɉɋ<<"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMOMOMPMPM1EPM1EPMoIPMoIPMenPMpenPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1f  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  aa)M*M44>5?5IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqee Y Y  MMAA11  " # %%'')k*k,,.W/W113C4C668/9/;;=>@@BCEuEuGGI]J]LLNEOEQQS-T-VVXY[[]]_q`qbbdYeYggiAjAlln)o)qqstvvxxzm{m}}UUɂɄ==""{{ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMCOMCOMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMPMPMPM`PM7PM7PM1QM1QMQML QMRM RMyRMp yRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xb. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xb. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xb. b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  XX)F*F44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjXX F F  44""u u""$c%c'')Q*Q,,.?/?113-4-6689;;= > @@BBDnEnGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMOMOMPMPM+EPM+EPMoIPMoIPM_nPMp_nPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1s  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  [[)C*C44>'?'IIS T ^}^}hhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo__ O O  ??// w w""$_%_'')G*G,,.///11346688:s;s==?W@WBBD;E;GGIJLLNOQuQuSSUYVYXXZ=[=]]_!`!bbdegwgwiik[l[nnp?q?ssu#v#xxz{}y}y]]τφ??!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMCOMCOMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMPMPMPM`PM7PM7PM1QM1QMQML QMRM RMgRMp gRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xd0 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xd0 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xd0 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  TT)>*>44>(?(IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjTT > >  ((qq[ [""$E%E'')/*/,,./11346x6x88:b;b==?L@LBBD6E6GGI J LLN O QQSSUiViXXZS[S]]_=`=bbd'e'ggijllnnpjqjssuNvNxxz2{2}}llމދPPސ44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMOMOMPMPM+EPM+EPM{IPM{IPM_nPMp_nPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1m  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  __)Q*Q44>A?AIIS-T-^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm__ Q Q  CC55''  " # %%'')v*v,,.h/h113Z4Z668L9L;;=>>>@@B0C0EEG"H"JJLMOOQQSuTuVVXcYc[[]Q^Q``b=c=eeg'h'jjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMsRMp sRMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1z} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1z} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k7 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1z  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ^^)J*J44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::..""  "#%%'(*x*x,,.d/d113P4P668<9<;;=(>(@@BCEEGHJtJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMOMOMPMPM%EPM%EPM{IPM{IPMYnPMpYnPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1~  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  YY)G*G44>3?3IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkYY G G  55##v v""$d%d'')R*R,,.@/@113.4.6689;;= > @@BBDoEoGGI[J[LLNEOEQQS/T/VVXY[[]^`x`xbbd^e^ggiDjDlln(o(qqs t v{v{xxz]{]}}??!!ssUU b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMPMPMPM`PM1PM1PM1QM1QMQML QMRM RMaRMp aRMSMt SM_TMT _TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1z} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1z} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1z  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>(?(IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI8J8LLNOQQSTVrVrXXZV[V]]_:`:bbdeggijltltnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMSOM SOMOMOMPMPM%EPM%EPMiIPMiIPMYnPMpYnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ii  YY)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1iiYY I I  99))   ""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnaoaqqsMtMvvx9y9{{}%~%ss__ՑՓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM7OM7OMPMPMEPMEPM LPM LPMnPMpnPM]PM]PM۵PM۵PMuPM`uPMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMMTMT MTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t@ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Oo  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  NN)8*844>?IIST^w^whhr[s[} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdegzgziik`l`nnpFqFssu,v,xxz{}}kkބކOO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOMPMPMEPMEPMiIPMiIPMSnPMpSnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS)?*?44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggSS ? ?  ++yye e""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMOM OM7OM7OMPMPMEPMEPM LPM LPMnPMpnPM]PM]PM۵PM۵PMPM`PMQMQM1QM1QMQML QMkRM kRMCRMp CRM}SMt }SMTMT TMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vB b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]i^ihhrIsI} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__aXbXddf:g:iiklnnpprosouuwQxQzz|3}3eeՋՍEE b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMMOM MOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1c  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>-?-IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIUJULLN?O?QQS)T)VVXY[[]]_r`rbbd\e\ggiFjFlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM!OM!OMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMPMPMuPM`uPMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}I b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1y} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}I b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1y} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1}I b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1y  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Vv  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  OO)9*944>"?"IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbRR B B  22""n n""$X%X'')B*B,,.,/,11346689;u;u==?_@_BBDIEIGGI2J2LLNOQQSTVvVvXXZ^[^]]_F`Fbbd8e8ggi j llnoq|q|ssudvdxxzL{L}}44zzdd b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMGOM GOMOMOM{PM{PMEPMEPMoIPMoIPMMnPMpMnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP):*:44>"?"IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI&J&LLN O QQSSUeVeXXZK[K]]_1`1bbdeggiikplpnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OM!OM!OMOM OM OM OMPMPMEPMEPMKPMKPMnPMpnPMcPMcPMPMPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1y} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1y} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1y  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1s  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>?IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGIJLLNOQxQxSSU^V^XXZD[D]]_*`*bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMGOM GOMOMOMuPMuPMEPMEPM]IPM]IPMGnPMpGnPMPMPM/PM/PM'PM`'PMcQMcQM1QM1QMQMT QMRM RMRMx RMSM| SMTM\ TMRUMRUMKeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1O-  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)C*C44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM'OM'OMOM OM+OM+OMPMPMEPMEPMKPMKPMnPMpnPMcPMcPMϵPMϵPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMłTMT łTMRUMRUMceUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1R b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  LL)D*D44>2?2IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^LL : :  (({{i i""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OMOMOMAOM AOMOMOMuPMuPMEPMEPM]IPM]IPMGnPMpGnPMPMPM/PM/PM'PM`'PMcQMcQM1QM1QMQMT QM}RM }RMRMx RMSM| SM5TM\ 5TM+RUM+RUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1_(  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  OO);*;44>?IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##k k""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM'OM'OMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMiPMiPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMkTMT kTMaRUMaRUM eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1T b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10^^  HH):*:44>$?$IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1^^HH 2 2  {{eeO O""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OM[OM[OMOM|OM]OM]OMOMOMOM|OMSOMHSOM'PM'PMDPMPDPM/JPMX/JPMeMPMeMPMVPMPVPM%ZPM%ZPMmPMmPMPM$ PMPM, PM7PM 7PMPM$ PMPM PM9PM| 9PM'PMX'PMcQMcQM-QM-QMcZ<|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:x\W'6r =  t  S  2   p O.,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__    )@*@44>+?+IIST^^his}s}} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //??) )""$_%_'')I*I,,.3/311346689;|;|==?f@fBBDPEPGGI;J;LLN#O#QQS T VVXXZg[g]]_O`ObbdCeCggi+j+llnoqqssuovoxxzW{W}}??''qq# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM9OM9OMOMdOMOMlOMOMOMKOMKOM PM@ PMEPMEPM]LPM]LPMUPM@UPMYPM YPMnPMnPM{PM{PM/PM /PMPM PMPMd PM1PM 1PMPM PMQMH QM/.QMh/.QMc bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _a> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _a>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 |( b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1_>N<|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:x9W~C6   t  S  2   r s Q0.n bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)@*@44>.?.IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$%'') * ,,..013'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbd]e]ggiGjGlln=o=qqs't'vvxy{{}}ppZZχωDD..  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OMUOMUOMOM|OM]OM]OMOMOMOM|OMSOMHSOM'PM'PMDPMPDPM/JPMX/JPMeMPMeMPMVPMPVPM%ZPM%ZPMmPMmPMPM$ PMPM, PM7PM 7PMPM$ PMPM PM9PM| 9PMPMXPM QM QMK-QMK-QM&?&IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##,, ""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _b> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _b>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 k&m b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1_> <|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:xW6 O  t   S Y  2    p O 8.,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM);*;44>%?%IIS T ^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$ % ''))+j,j..013 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpeqessuKvKxxz1{1}}ppVVɎɐ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMAOMdAOMOMlOMOMOMQOMQOMuPM@uPMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMGnPMGnPMPMPM5PM 5PMPM PMPMd PM7PM 7PM-PM -PMiQMP iQM-QMp-QMiU<|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:xKW6]&   t  S  2   p O.,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  MM);*;44>+?+IISS]^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__MM ; ;  ))||j j""$X%X'')F*F,,.4/4113"4"6689;;==?u@uBBDcEcGGISJSLLNAOAQQS/T/VVXY[[] ^ ``bbd.e.ggijllnQoQqqs5t5vvxy{{}}ooSSŇʼn77  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM3OM3OMOMdOMOMlOMOMOMKOMKOMPM@PMEPMEPM]LPM]LPMUPM@UPMYPM YPMnPMnPMuPMuPM/PM /PMPM PMPMd PM1PM 1PMPM PM?QMH ?QM-QMh-QM bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 o b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1iR$dh  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1diR;$ v_H3`0  t _ J 5  4t I]H bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)B*B44>,?,IISS]^hhrrsr} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffZZ N N  BB66&&  ""$t%t'')`*`,,.L/L113848668$9$;;=>@@BBDlElGGITJTLLN <|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:xW6 o  t 8  S   2 J   p O.n.,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  II)3*344>?IISS]^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__II 3 3  ||ffP P""$:%:'')$*$,,./11335m6m88:W;W==?A@ABBD+E+GGIJLLNOQvQvSSU`V`XXZJ[J]]_4`4bfbfddfPgPiik:l:nnpiqissuMvMxxz1{1}}kk݉݋OO33  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM9OM9OMOMdOMOMlOMOMOMKOMKOM PM@ PMEPMEPM]LPM]LPMUPM@UPMYPM YPMnPMnPM{PM{PM/PM /PMPM PMPMd PM1PM 1PMPM PMKQMH KQM-QMh-QMi bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 f b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1_> <|  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d_>|[:xW6  t P  S  2 p   @ p O.,l bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)8*844>?IISS]x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$l l""$T%T'')<*<,,.$/$113 4 6688:h;h==?N@NBBD2E2GGIJLLNNPlQlSSUPVPXXZ4[4]]_`bKbKddf/g/iiklnnp:q:ssuvxxz{}t}tXXʄʆ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMWQM8 WQM-QMX-QM99QM499QMwQMwQMRM,RMgRMgRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 U_> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 U_> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 U_>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1z$ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1N bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18F ~  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  WW)C*C44>/?/IIST^^hhrsss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccWW K K  ??33''  "#%%'')q*q,,.]/]113I4I668595;;=!>!@@B C EEGGIoJoLLNWOWQQS?T?VVX'Y'[[]^``bbdkekggiSjSlln;o;qqs#t#vvx y {{}}ggۂۄOOÇÉ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM-OM-OMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMoPMoPM;PM ;PMſPM ſPMPML PM=PM =PMPM PM'QM0 'QMi-QMPi-QMi9QM,i9QMQMQMRM$RMsRMsRMSMSMTMTMTUMTUMmgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _wB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _wB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _wB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 b b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1:z bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hC y : } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  XX)J*J44>7@@B)C)EEGHJJL M OOQQSpTpVVX^Y^[[]L^L``b8c8eeg"h"jjl m ooqqsetevvxKyK{{}1~1ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMGOMLGOMOMTOMOMOMQOMQOM{PM({PMEPMEPMcLPMcLPMUPM(UPM#YPM#YPMMnPMMnPMPMPM5PM 5PMPM PMPML PM7PM 7PMPM PMQM8 QME-QMXE-QM;QM4;QMQMQMwRM,wRMORMORMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 V_> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 V_> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 V_>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1gcc;c b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1T  b ) E } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  SS);*;44>#?#IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33## { {""$g%g'')O*O,,.7/711346689;{;{==?c@cBBDKEKGGI3J3LLNOQQSSUmVmXXZQ[Q]]_5`5bbdeggiikolonnpSqSssu7v7xxz{}}qqUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM3OM3OMOMLOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMnPMnPMoPMoPM;PM ;PMſPM ſPMPML PM=PM =PMPM PM?QM0 ?QM-QMP-QM.?.IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIVJVLLN@O@QQS*T*VVXY[[]]_s`sbbdYeYggi?j?lln#o#qqstvvvvxxzX{X}}::ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMMOMLMOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMSnPMSnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMQM8 QM.QMX.QMQ9QM4Q9QM+QM+QM}RM,}RMURMURMSMSMMTMMTMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @a@ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @a@ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @a@  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1od b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 ` bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1R$v 0p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10``  KK)5*544>?IIST^v^vhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1``LL 8 8  $$ppZ Z""$D%D'').*.,,./11346w6w88:a;a==?I@IBBD/E/GGIJLLNNPnQnSSUTVTXXZ:[:]]_ ` bbdegygyiik_l_nnpEqEssu+v+xxz{}}jj݄݆PP‰‹44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM'OM'OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMiPMiPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QMW-QMPW-QM9QM,9QMQMQMRM$RMyRMyRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _ M bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _ M bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _ M  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Uu b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1P bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1@& r  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>6?6IIS"T"^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGIvJvLLNbObQQSNTNVVX:Y:[[]&^&``bceeggitjtlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMMOMLMOMOMTOM!OM!OMWOMWOM{PM({PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMMnPMMnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMcPM cPMQM8 QM-QMX-QM;QM4;QMQMQMkRM,kRMCRMCRM}SM}SMTMTMSUMSUMefUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @`? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @`? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1a   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @`?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1`\\4CcW b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 H  l >  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  KK)1*144>?IISS]h^hhhrJsJ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&nnT T""$:%:'') * ,,./1y1y335_6_88:E;E==?)@)BBD E G|G|IIK^L^NNP@Q@SSU"V"XXZ[]u]u__aWbWddf9g9iiklnnpprnsnuuwPxPzz|2}2ff֋֍FF b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM-OM-OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMiPMiPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PM3QM0 3QMu-QMPu-QM' $ f } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>(?(IIST^^hhrlsl} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI8J8LLN O QQSTV|V|XXZd[d]]_L`Lbbd4e4ggijllnoqxqxssu`v`xxzH{H}}00tt\\ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMSOMLSOMOMTOM9OM9OMoOMoOMPM(PM%EPM%EPMLPMLPM VPM( VPMAYPMAYPMYnPMYnPMPMPMSPM SPMݿPM ݿPMPML PMUPM UPMPM PMQM8 QM#.QMX#.QMi9QM4i9QMQMQMRM,RMgRMgRMSMSMTMTMkTUMkTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IwV bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IwV bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IwV  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1d b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations16v bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X5 o 6 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  PP):*:44>%?%IIS T ^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccSS C C  33##o o""$Y%Y'')C*C,,.-/-11346689;v;v==?`@`BBDJEJGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--uu__ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM!OM!OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPM]PM]PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMPM0 PM?-QMP?-QM9QM,9QMQMQMRM$RMsRMsRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _wA bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _wA bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _wA  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Hh b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1f bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 z k  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  TT)B*B44>0?0IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffTT B B  00  q q""$_%_'')M*M,,.;/;113)4)6689;;=>@|@|BBDjEjGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd_e_ggiIjIlln3o3qqstvvxy{|{|}}ffۂۄPPŇʼn::$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMSOMLSOMOMTOM9OM9OMoOMoOMPM(PMEPMEPMLPMLPM VPM( VPMAYPMAYPMSnPMSnPMPMPMSPM SPMݿPM ݿPMPML PMUPM UPMPM PMQM8 QM .QMX .QM "?"IIST^y^yhhr_s_} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccOO ; ;  ''ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?N@NBBD8E8GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆOO‰‹55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM!OM!OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMcPMcPMAPM APM˿PM ˿PMPML PMCPM CPMPM PM!QM0 !QMc-QMPc-QMK /7w } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ);*;44>%?%IIS T ^~^~hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI)J)LLNOQQSSUhVhXXZN[N]]_4`4bbdeggijlslsnnpYqYssu?v?xxz%{%}} ~~dd׉׋JJ00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMYOMLYOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM8 QM/.QMX/.QM9QM49QMÐQMÐQMRM,RMsRMsRMSMSMłTMłTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @`? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @`? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @`?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1Yy b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1L bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations10 h  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>/?/IIST^^hissss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGIWJWLLNEOEQQS3T3VVX!Y![[]^``bbdtetggibjbllnKoKqqs/t/vvxy{{}}iiۂۄMM11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMWPMWPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM/.QMP/.QM9QM,9QMOQMOQMRM$RMsRMsRMSMSMTMTMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m9  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ;[ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1| bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1pl h d L } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)F*F44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj^^ R R  FF::**  "#%x%x'')d*d,,.P/P113<4<668(9(;;=>@@BBDpEpGGIXJXLLN@O@QQS(T(VVXY[[]]_l`lbbdTeTggi#?#IIS T ^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccMM 7 7  !!  jjT T""$>%>'')(*(,,./11335q6q88:[;[==?E@EBBD/E/GGIJLLNOQzQzSSUdVdXXZN[N]]_8`8bbd"e"ggi j llnnpeqessuIvIxxz-{-}}ggىًKK// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPM]PM]PMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM.QMP.QMo"?"IIST^x^xhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((p p""$X%X'')@*@,,.(/(11346688:l;l==?R@RBBD6E6GGIJLLNNPpQpSSUTVTXXZ8[8]]_`bbdegrgriikVlVnnp:q:ssuvxxz{}t}tXXʄʆ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOM_OML_OMOMTOM-OM-OMcOMcOMPM(PM+EPM+EPMuLPMuLPMUPM(UPM5YPM5YPM_nPM_nPMPMPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM8 QM).QMX).QM9QM49QMQMQMRM,RMyRMyRMSMSMׂTMׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @`? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @`? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @`?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1Nn b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1b bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1{n a  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  [[)G*G44>3?3IIST^^hiswsw} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77++  "#%%'')u*u,,.a/a113M4M668999;;=%>%@@BCEEGGIsJsLLN[O[QQSCTCVVX+Y+[[]^``bbdoeoggiWjWlln?o?qqs't'vvxy{{}}kk߂߄SSLJlj;;## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMQPMQPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM5.QMP5.QM9QM,9QMQMQMRM$RMRMRMSMSM TM TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb. b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _y> bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb. b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _y> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1vb.  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _y>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 .Nw b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1HO V ] R } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJLMOOQQStTtVVXbYb[[]P^P``b'?'IIS T ^}^}hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''  ""$k%k'')S*S,,.;/;113#4#668 9 ;;==?g@gBBDOEOGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMWPMWPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM/.QMP/.QM bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xf2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _x> bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xf2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _x>  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 9Y b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1Y  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d k ry } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNDODQQS.T.VVXY[[]^`w`wbbd]e]ggiCjClln'o'qqs t vzvzxxz\{\}}>> ttVV b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOM_OML_OMOMTOM3OM3OMiOMiOMPM(PM1EPM1EPM{LPM{LPMVPM(VPM;YPM;YPMenPMenPMPMPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMPM8 PM?-QMX?-QM9QM49QMUQMUQMRM,RMgRMgRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @`? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @`? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @`?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1Cc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1x bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`^ \ Z H } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  OO)9*944>!?!IIST^z^zhhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnTTƉƋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OM OM OMOMLOMOMTOM3OM3OMiOMiOMPM(PMyEPMyEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMKPMKPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM5.QMP5.QM9QM,9QMQMQMRM$RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 _? bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 _? bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1kW#  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 _?  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 !Aa b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 2 D V  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)J*J44>:?:IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$r%r'')b*b,,.R/R113B4B668292;;=">"@@BCEEGHJzJzLLNfOfQQSRTRVVX>Y>[[]*^*``bceeghjxjxllndodqqsPtPvvx?IISS]l^lhhrNsN} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **rrX X""$>%>'')$*$,,. / 1}1}335c6c88:I;I==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6jjڋڍJJ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMQPMQPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM5.QMP5.QM,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$R%R'')>*>,,.*/*11346689;x;x==?d@dBBDPEPGGI8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88%%  ""$n%n'')X*X,,.B/B113,4,6689;;=>@u@uBBD_E_GGIHJHLLN0O0QQSTVVXY[t[t]]_\`\bbdDeDggi,j,llnoqqssupvpxxzX{X}}@@((pp b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OM OM OMOM OM7OM7OMPMPMsEPMsEPM LPM LPMnPMpnPMEPMEPM۵PM۵PMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMTUMTUMggUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_K b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_K b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_K b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1k  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  aa)O*O44>;?;IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssaa O O  ==++ ~ ~""$l%l'')Z*Z,,.H/H113646668$9$;;=>@@BCEwEwGGIcJcLLNMOMQQS7T7VVX!Y![[] ^ ``bbdjejggiTjTlln>o>qqs(t(vvxy{{}}qq[[ЇЉEE// b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OMٚOMٚOMwOMwOMOM$OMPMPMIEPMIEPM{IPM${IPM}nPM}nPMPMPMMPM$MPMPMPMCPMCPM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMwTM wTMGTUMGTUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14u b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14u b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14u b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  aa)K*K44>3?3IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvbb N N  ::&&p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI3J3LLNOQQSSUrVrXXZX[X]]_>`>bbd"e"ggijlxlxnnp\q\ssu@v@xxz${$}}zz^^щыDD** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OM OM OMOM OM7OM7OMPMPMyEPMyEPM LPM LPMnPMpnPMKPMKPM۵PM۵PMPM`PMQMQM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1_M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1v  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ``)J*J44>2?2IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$r r""$]%]'')G*G,,.1/111346689;z;z==?d@dBBDNENGGI6J6LLNOQQSTVuVuXXZ[[[]]_A`Abbd'e'ggi j llnnpfqfssuLvLxxz2{2}}qqWWʎʐ== b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPM{IPM{IPMwnPMpwnPMPMPMMPMMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>?>IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ttbb P P  >>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIfJfLLNTOTQQSBTBVVX0Y0[[]^``b c eeggiqjqllnZoZqqs>t>vvx"y"{{}~xx\\·Ή@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OM OM OMOM OMCOMCOMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hT  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hT  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hT  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  cc)O*O44>7?7IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ssgg [ [  OOCC33  " # %%'')m*m,,.Y/Y113E4E668191;;=>@@BCEwEwGGI_J_LLNGOGQQS/T/VVXY[[]]_s`sbbd[e[ggiCjClln+o+qqstvvxxzo{o}}WW˂˄??$$ }} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPM{IPM{IPMwnPMpwnPMPMPMMPMMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMyRMp yRMSMt SMTMT TMSTUMSTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1r b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  \\)F*F44>0?0IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr\\ F F  00yyc c""$M%M'')7*7,,.!/!113 4 6688:j;j==?T@TBBD>E>GGI(J(LLNOQQSSUqVqXXZ[[[]]_E`Ebbd/e/ggijllnoqrqrssuVvVxxz:{:}}ttXXʎʐ<< b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OMCOMCOMPMPMyEPMyEPMLPMLPMnPMpnPMKPMKPMPMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMmRMp mRMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hV" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hV" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1hV" b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ss  __)G*G44>+?+IIST^^hhrcsc} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1sscc S S  CC33 { {""$c%c'')K*K,,.3/311346689;w;w==?[@[BBD?E?GGI#J#LLNOQyQySSU]V]XXZA[A]]_%`%bbd e g{g{iik_l_nnpCqCssu'v'xxz { }}}}aaӄӆCC%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMIPMIPMqnPMpqnPMPMPMSPMSPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TMTUMTUMagUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  hh)T*T44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tthh \ \  PPDD88,,  " # %%' ( **,,.n/n113Z4Z668F9F;;=2>2@@BCEEG H J~J~LLNfOfQQSNTNVVX6Y6[[]^``bcezezggibjbllnJoJqqs2t2vvxy{{}~vv^^҇҉FF.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q]) b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q]) b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q]) b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  aa)S*S44>C?CIIS/T/^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ooaa S S  EE77))  " # %%'')x*x,,.j/j113\4\668N9N;;=@>@@@B2C2EEG$H$JJLMOOQRTwTwVVXeYe[[]S^S``b?c?eeg)h)jjlmooqqsltlvvxRyR{{}8~8ttXXʑʓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMOMOMPMPM7EPM7EPMIPMIPMknPMpknPM PM PMSPMSPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)J*J44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%v%v'')^*^,,.F/F113.4.6689;;==?r@rBBDZEZGGI@J@LLN$O$QQSTVzVzXXZ^[^]]_B`Bbbd&e&ggi j l|l|nnp`q`ssuDvDxxz({(}} ~~bbԉԋFF** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMQPMQPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMyRMp yRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q_+ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10oo  ]])K*K44>7?7IIST^^hisqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1oo]] K K  99'' z z""$h%h'')V*V,,.D/D113242668 9 ;;=>@@BBDsEsGGI_J_LLNIOIQQS3T3VVXY[[]^`|`|bbdbebggiHjHlln,o,qqstvvxxza{a}}CC%%wwYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMoIPMoIPMknPMpknPM PM PMAPMAPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  XX)B*B44>(?(IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11}}g g""$Q%Q'');*;,,.%/%11346688:n;n==?T@TBBD:E:GGI J LLNOQyQySSU_V_XXZE[E]]_+`+bbdeggiikjljnnpPqPssu6v6xxz{}}uuYYˉˋ==!! b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPMWPMWPMPMPMPM`PM7PM7PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zf2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zf2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zf2 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  [[)K*K44>9?9IIS%T%^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kk[[ K K  ;;++   ""$s%s'')c*c,,.S/S113C4C668393;;=#>#@@BCEEGHJyJyLLNeOeQQSQTQVVX=Y=[[])^)``bceeghjwjwllncocqqsOtOvvx;y;{{}'~'uuaaבד b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM1EPM1EPMoIPMoIPMenPMpenPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QM}RM }RMURMp URMSMt SMTMT TMSUMSUMwfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1l b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1n  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  VV)<*<44>?IIST^q^qhhrQsQ} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11yy_ _""$E%E'')+*+,,./11335j6j88:P;P==?2@2BBDEGGIIKgLgNNPIQISSU+V+XXZ [ ]~]~__a`b`ddfBgBiik$l$nnpqswswuuwYxYzz|;};mm݋ݍMM b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPMWPMWPMPMPMPM`PM7PM7PM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zh4 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zh4 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zh4 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10kk  WW)C*C44>-?-IIST^^hhrqsq} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1kkWW C C  //}}i i""$U%U'')A*A,,.-/-11346689;{;{==?g@gBBDSESGGI=J=LLN%O%QQS T VVXXZi[i]]_Q`Qbbd9e9ggi!j!lln o q}q}ssuevexxzM{M}}55yyaa b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMOMOMPMPM1EPM1EPM{IPM{IPMenPMpenPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SMTMT TMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  YY)C*C44>,?,IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, x x""$b%b'')L*L,,.6/6113 4 668 9 ;;==?i@iBBDSESGGI/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggUU C C  11  r r""$`%`'')N*N,,.@}@}BBDkEkGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMYOM YOMOMOMPMPM+EPM+EPM{IPM{IPM_nPMp_nPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1i b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1y  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  UU)?*?44>'?'IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjVV B B  ..zzd d""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiiklllnnpPqPssu4v4xxz{}}nnRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMPMPMPM`PM7PM7PM1QM1QMQML QMRM RMaRMp aRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1x} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1x} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1x  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  TT)>*>44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,zzf f""$Q%Q'');*;,,.%/%11346688:n;n==?X@XBBDBEBGGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOMOMOMPMPM+EPM+EPMiIPMiIPM_nPMp_nPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1m  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>2?2IIS T ^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIZJZLLNHOHQQS6T6VVX$Y$[[]^``bcewewggiejellnNoNqqs2t2vvxy{{}}llނބPP‡‰44 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM!OM!OMOM OM=OM=OMPMPMEPMEPMLPMLPMnPMpnPM]PM]PMPMPM{PM`{PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xD b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1Xx  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  WW)C*C44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1gg[[ O O  CC77''  ""$u%u'')a*a,,.M/M113949668%9%;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33qq b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMSOM SOMOMOMPMPM%EPM%EPMiIPMiIPMYnPMpYnPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>$?$IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ{Q{SSUeVeXXZO[O]]_9`9bbd#e#ggi j llnnpfqfssuJvJxxz.{.}}hhډڋLL00 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM!OM!OMOM OM=OM=OMPMPMEPMEPMLPMLPMnPMpnPMcPMcPMPMPMPM`PMQMQM1QM1QMQML QMwRM wRMORMp ORMSMt SM5TMT 5TMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zF b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1q  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10gg  SS);*;44>?IIST^u^uhhrWsW} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ggWW G G  77''o o""$W%W'')?*?,,.'/'11346688:k;k==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMSOM SOMOMOMPMPMEPMEPMuIPMuIPMSnPMpSnPMPMPMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMmRMp mRMSMt SM˂TMT ˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1j  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>2?2IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGIrJrLLNZOZQQSBTBVVX*Y*[[]^``bbdnenggiVjVlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM'OM'OMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMcPMcPMPMPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SMTMT TMTUMTUMsgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1M b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1_  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  UU)G*G44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccUU G G  99++  "#%z%z'')l*l,,.^/^113P4P668B9B;;=4>4@@B&C&EEGHJJLMO}O}QQSkTkVVXYYY[[]G^G``b3c3eeghjjlmooqqsjtjvvxPyP{{}6~6rrVVȑȓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMMOM MOMOMOMPMPMEPMEPMoIPMoIPMSnPMpSnPMPMPMAPMAPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)>*>44>$?$IIST^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI4J4LLNOQQSSUnVnXXZR[R]]_6`6bbdeggiikplpnnpXqXssu>"" b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM'OM'OMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMiPMiPMPMPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMTMT TMYTUMYTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1w} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1w} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1O b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1w  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10cc  QQ)?*?44>+?+IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ccQQ ? ?  --  n n""$\%\'')J*J,,.8/8113&4&6689;;=>@y@yBBDgEgGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdVeVggi?IIST^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss] ]""$G%G'')1*1,,./11346z6z88:d;d==?J@JBBD0E0GGIJLLNNPoQoSSUUVUXXZ;[;]]_!`!bbdeggiiklllnnpRqRssu8v8xxz{}}ww[[͉͋??## b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM'OM'OMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMiPMiPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TM SUM SUMeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1V b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  OO)I*I44>7?7IIS#T#^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__OO ? ?  //w w""$q%q'')a*a,,.Q/Q113A4A668191;;=!>!@@BCEEGHJwJwLLNcOcQQSOTOVVX;Y;[[]'^'``bceeggiujullnmomqqsYtYvvxEyE{{}1~1 kk b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OMOMOMGOM GOMOMOM{PM{PMEPMEPMcIPMcIPMMnPMpMnPMPMPM5PM5PM!PM`!PM]QM]QM1QM1QMQMT QMqRM qRMRMx RMwSM| wSMTM\ TMQUMQUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1`  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7M'operation.3exchange :z2breasonOperatorInputsvalue7invocations1V!  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  NN)4*444>?IIST^u^uhhrUsU} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?*@*BBD E G}G}IIK_L_NNPAQASSU#V#XXZ[]v]v__adbdddfFgFiik(l(nnp q s{s{uuw]x]zz|?}?!!qqQQ b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM-OM-OMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMiPMiPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMRUMRUM9eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1X b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10__  KK)?*?44>)?)IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1__KK 7 7  ##qq] ]""$Q%Q'')=*=,,.)/)11346689;w;w==?c@cBBDOEOGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqqssumvmxxzU{U}}==%% ii b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1OM[OM[OMOM|OM]OM]OMOMOMOM|OMSOMHSOM-PM-PMDPMPDPM/JPMX/JPMeMPMeMPMVPMPVPM%ZPM%ZPMmPMmPMPM$ PMPM, PM7PM 7PMPM$ PMPM PM9PM| 9PMPMXPMQMQMQ-QMQ-QMo1?1IIS%T%^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11SS? ?""$y%y'')e*e,,.Q/Q113=4=668)9);;=>@@BBDqEqGGIYJYLLNAOAQQS)T)VVXY[[]]_m`mbbdaeaggiIjIlln1o1qqstvvxy{u{u}}]]тфEE,,# b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM?OM?OMOMdOMOMlOMOMOMQOMQOMPM@PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMnPMnPMPMPM5PM 5PMPM PMPMd PM7PM 7PMPM PM9QMH 9QM{-QMh{-QM ? IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%// ""$G%G'')1*1,,./11346z6z88:d;d==?L@LBBD2E2GGIJLLNNPqQqSSUWVWXXZ=[=]]_#`#bbdeggiiknlnnnpTqTssu:v:xxz { }}yy__щыCC''  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1OM[OM[OMOM|OM]OM]OMOMOMOM|OMSOMHSOM'PM'PMDPMPDPM/JPMX/JPMeMPMeMPMVPMPVPM%ZPM%ZPMmPMmPMPM$ PMPM, PM7PM 7PMPM$ PMPM PM5PM| 5PMEPMTEPMQMQM.QM.QM#?#IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!!<<$ $""$Y%Y'')A*A,,.)/)11346688:m;m==?S@SBBD7E7GGIJLLNNPqQqSSUUVUXXZ9[9]]_`bbd e ggiikclcnnpGqGssu+v+xxz{}}eeׄ׆II++ # b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 $ bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMEOMEOMOMdOMOMlOMOMOMQOMQOMPM@PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMnPMnPMPMPM5PM 5PMPM PMPMd PM7PM 7PM9PM 9PMuQMH uQM-QMh-QM=QMD=QMqQMqQMkQMkQMiQM iQMkRMkRMCRMpCRM}SMt}SMSMTSMTMTMSUM$SUMefUM(} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1x b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 a^B bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1x b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 a^B bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1x  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 a^B  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ~(H b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7MWoperation.4exchange :z2breasonOperatorInputsvalue8invocations1T\$  b-g operation.4ipu_stack_rearrange_row_major_to_amp_f16_o1_r64_p64_c72_p80-:-z1211Z5z*z*breasonOperatorInputsvalue8kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(TransposedRight), tiling: TensorTiling { tile_count: 192, replicas: 1, axes: [AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(2), partitions: 12, block_size: 64, padding_multiple: 64, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements4608input0Elements4608invocations1 bJ7Moperation.5exchange :z2breasonOperatorInputsvalue9invocations1d (d2+<rFPX  `  h  p  x * Z$t bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa    )4*444>?IIST^w^whhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%,, ""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__afbfddfHgHiik*l*nnp q s}s}uuw_x_zz|A}A##uuUUŐŒ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMGOMdGOMOMlOMOMOMQOMQOM{PM@{PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMMnPMMnPMPMPM5PM 5PMPM PMPMd PM7PM 7PMPM PM QMP  QMK-QMpK-QMu7?7IISS]^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaSS E E  77))   ""$x%x'')j*j,,.\/\113N4N668@9@;;=2>2@@B$C$EEGHJJLMO}O}QQSkTkVVXYYY[[]G^G``bbddedggiNjNllnoqqsjtjvvxPyP{{}6~6ttXXʑʓ  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM9OM9OMOMdOMOMlOMOMOMQOMQOM PM@ PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMnPMnPM{PM{PM5PM 5PMPM PMPMd PM7PM 7PMPM PM-QMH -QMo-QMho-QMu&?&IISS]^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddTT D D  44$$p p""$Z%Z'')D*D,,../.11346689;w;w==?a@aBBDKEKGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jb|b|ddfdgdiikLlLnoqxqxssu`v`xxzH{H}}00xxbb  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOMOMOMGOMdGOMOMlOMOMOMQOMQOM{PM@{PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMMnPMMnPMPMPM5PM 5PMPM PMPMd PM3PM 3PMoPM oPMQMD QM.QMd.QMu+?+IISS]^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdeggiikjljn(o(qqs t v{v{xxz]{]}}??!!uuWW  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1xOM?OM?OMOMdOMOMlOMOMOMQOMQOM PM@ PMEPMEPMcLPMcLPMUPM@UPM#YPM #YPMnPMnPM{PM{PM5PM 5PMPM PMPMd PM7PM 7PM'PM 'PMcQMH cQM-QMh-QMuiJ+   m  N  /   qRT bWuoperation.6ipu_stack_copy_u64%:%R)2))2)2)B)Z-b1reasonLocalCopyvalue10bytes10240patternContiguousinvocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  MM)7*744>!?!IISS]|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bWuoperation.6ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue10bytes2048patternContiguousinvocations5 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&rr\ \""$F%F'')0*0,,./11346y6y88:c;c==?M@MBBD7E7GGI!J!LLNOQzQzSSU`V`XXZF[F]]_,`,b]b]ddfAgAiik%l%nnpNqNssu2v2xxz{}}llބކRRʼnŋ88  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1! bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMMOMLMOMOMTOM!OM!OMWOMWOMPM(PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMSnPMSnPMPMPM;PM ;PMſPM ſPMPML PM=PM =PMPM PMPM8 PM9-QMX9-QM/4QM4/4QM?QM?QMRM,RMsRMsRMSMSMTMTMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 UaB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 UaB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 UaB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1{w|   b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1I[H } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>1?1IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$i%i'')Y*Y,,.I/I113949668)9);;=>@@B C EEGGIqJqLLN]O]QQSITIVVX5Y5[[]!^!``b c eeggiojolln[o[qqsGtGvvx3y3{{}~ mmYYϑϓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM3OM3OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMuPMuPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQM0 QM]-QMP]-QM/4QM,/4QMQMQMRM$RMgRMgRMSMSMTMTMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 auF bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 auF bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1^  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 auF  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Ll b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1]:  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  RR)@*@44>0?0IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddRR @ @  ..  o o""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGIXJXLLNFOFQQS4T4VVX"Y"[[]^``bbdueuggicjcllnLoLqqs0t0vvxy{{}}jj܂܄NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OMOMOMMOMLMOMOMTOM!OM!OMWOMWOM{PM({PMEPMEPMiLPMiLPMUPM(UPM)YPM)YPMMnPMMnPMPMPM;PM ;PMſPM ſPMPML PM9PM 9PMPM PMQM, QM /QML /QM5QM$5QMɇQMɇQMRMRM[RM[RMSMSMTMTMYTUMYTUMgUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 VaB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 VaB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b   b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 VaB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 [WWu b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$m6 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM)9*944>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$K%K'')7*7,,.#/#11346688:q;q==?]@]BBDIEIGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--qqYY b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l!OM9OM9OMOMLOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMnPMnPMuPMuPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMQQM0 QQM-QMP-QM6QM,6QMUQMUQM}RM$}RMURMURMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 auG bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 auG bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 auG  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 l b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1tQ. ] } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  LL)6*644>"?"IIS T ^~^~hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbLL 6 6      iiS S""$=%='')'*',,./11335p6p88:Z;Z==?D@DBBD.E.GGIJLLNOQyQySSUcVcXXZM[M]]_7`7bbd!e!ggi j llnnpdqdssuHvHxxz,{,}}ff؉؋JJ.. b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMSOMLSOMOMTOM'OM'OM]OM]OMPM(PM%EPM%EPMoLPMoLPMUPM(UPM/YPM/YPMYnPMYnPMPMPMAPM APM˿PM ˿PMPML PMCPM CPMPM PMPM8 PM--QMX--QM54QM454QMQMQMRM,RMmRMmRMSMSM˂TM˂TMTUMTUMCgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @cD bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @cD bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @cD  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1rnn b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1B bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1V*~ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hhrtst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLN=O=QQS'T'VVXY[[]]_p`pbbdZeZggiDjDlln.o.qqstvvxy{w{w}}aaւքKK55 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM-OM-OMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMiPMiPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QMQ-QMPQ-QM/4QM,/4QMmQMmQMRM$RMmRMmRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 aQ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 aQ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 aQ  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Cc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1hP8p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  \\)H*H44>4?4IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hh\\ P P  DD88,,   "#%%'(*v*v,,.b/b113N4N668:9:;;=&>&@@BCEEGGItJtLLN\O\QQSDTDVVX,Y,[[]^``bbdpepggiXjXlln@o@qqs(t(vvxy{{}}llTTȇȉ<<$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMSOMLSOMOMTOM'OM'OM]OM]OMPM(PMEPMEPMoLPMoLPMUPM(UPM/YPM/YPMSnPMSnPMPMPMAPM APM˿PM ˿PMPML PM?PM ?PMPM PMQM, QM/QML/QM5QM$5QM5QM5QMRMRM[RM[RMSMSMeTMeTM5TUM5TUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1c  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 PLLz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1R&zN6v } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  NN)8*844>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbNN : :  &&tt` `""$K%K'')5*5,,./113 4 6~6~88:h;h==?R@RBBD*>44>&?&IIS T ^|^|hhr`s`} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$j%j'')R*R,,.:/:113"4"668 9 ;~;~==?f@fBBDNENGGI6J6LLNOQQSSUpVpXXZT[T]]_8`8bbdeggijlrlrnnpVqVssu:v:xxz{}}ttXXʉʋ<<  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMYOMLYOMOMTOM?OM?OMuOMuOMPM(PM%EPM%EPMLPMLPMVPM(VPMGYPMGYPMYnPMYnPMPMPMYPM YPMPM PMPML PM[PM [PMPM PMQM8 QM.QMX.QM54QM454QMÇQMÇQMRM,RMmRMmRMSMSMTMTM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  IyZ bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  IyZ bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  IyZ  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1eaaz b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1X0 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)A*A44>+?+IIST^^hhroso} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeYY M M  AA55%%  ""$s%s'')_*_,,.K/K113747668#9#;;=>@@BBDkEkGGISJSLLN;O;QQS#T#VVX Y [[]]_g`gbbdOeOggi7j7llnoqqstv{v{xxzc{c}}KK33ss b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM'OM'OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMcPMcPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM.QMP.QM54QM,54QM!QM!QMRM$RM[RM[RMSMSMYTMYTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 auE bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 auE bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 auE  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 :Zq b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1sfY ` } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^{^{hhrasa} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?N@NBBD4E4GGIJLLNOQsQsSSUYVYXXZ?[?]]_%`%bbd e g~g~iikdldnnpJqJssu0v0xxz{}}ooUUljNj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OMOMOMSOMLSOMOMTOM?OM?OMuOMuOMPM(PM%EPM%EPMLPMLPMVPM(VPMGYPMGYPMYnPMYnPMPMPMYPM YPMPM PMPML PMWPM WPMPM PMQM, QM/QML/QM5QM$5QMYQMYQM}RM}RMURMURMSMSM5TM5TMTUMTUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1  JxY bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1  JxY bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1  JxY  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 EAAc b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1`8hX } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)9*944>?IIST^u^uhhrYsY} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%m m""$U%U'')=*=,,.%/%113 4 6688:i;i==?O@OBBD3E3GGIJLLNNPmQmSSUQVQXXZ5[5]]_`bbddfogoiikSlSnnp7q7ssuvxxzz|q}qUUDŽdž99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l'OM'OM'OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMiPMiPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM-QMP-QM6QM,6QMՐQMՐQMqRM$qRMIRMIRMSMSMTMTMSUMSUMkfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 auF bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 auF bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1L  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 auF  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ZzXx b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1L?2% } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  NN)4*444>?IISS]k^khhrMsM} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))qqW W""$=%='')#*#,,. / 1|1|335b6b88:H;H==?,@,BBDEGGIIKaLaNNPCQCSSU%V%XXZ[]x]x__aZbZddf;?;IIS'T'^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeWW I I  ;;--  "#%|%|'')n*n,,.`/`113R4R668D9D;;=6>6@@B(C(EEGHJJL M OOQQSoToVVX]Y][[]K^K``b7c7eeg!h!jjl m o~o~qqsdtdvvxJyJ{{}0~0nnRRđē b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPM]PM]PMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM5.QMP5.QM;4QM,;4QMՐQMՐQMRM$RMmRMmRMSMSMTMTMqTUMqTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 aC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q= b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 aC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q=  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 aC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 1Q b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1~|z } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  UU)?*?44>*?*IIST^^hhrpsp} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhXX H H  88((t t""$^%^'')H*H,,.2/211346689;{;{==?e@eBBDOEOGGI:J:LLN"O"QQS T V~V~XXZf[f]]_N`Nbbd6e6ggijllnoqzqzssubvbxxzJ{J}}22zzdd b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OMOMOMYOMLYOMOMTOM-OM-OMcOMcOMPM(PM+EPM+EPMuLPMuLPMUPM(UPM5YPM5YPM_nPM_nPMPMPMGPM GPMѿPM ѿPMPML PMEPM EPMPM PMQM, QM%/QML%/QM5QM$5QMQMQMRMRMmRMmRMSMSMTMTM_TUM_TUMgUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 :66~ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1 oR5 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbdZeZggi@j@lln$o$qqstvwvwxxzY{Y}};;qqSS b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l-OM!OM!OMOMLOMOMTOM-OM-OMcOMcOMPM(PMEPMEPMuLPMuLPMUPM(UPM5YPM5YPMnPMnPMcPMcPMGPM GPMѿPM ѿPMPML PMIPM IPMPM PMQM0 QM#.QMP#.QM6QM,6QMQMQMRM$RMaRMaRMSMSM_TM_TM/TUM/TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 aC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 aC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1uA  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 aC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 Qq{ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1xvtr } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>%?%IIS T ^|^|hhrbsb} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?Q@QBBD;E;GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikjljnnpNqNssu2v2xxz{}}llބކRRʼnŋ88 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOM_OML_OMOMTOM3OM3OMiOMiOMPM(PM1EPM1EPM{LPM{LPMVPM(VPM;YPM;YPMenPMenPMPMPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM8 QM/.QMX/.QM;4QM4;4QMwQMwQMRM,RMRMRMSMSMTMTMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1OKK b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1n\Jp } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  UU)E*E44>5?5IIS!T!^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%% } }""$m%m'')]*],,.M/M113=4=668-9-;;=>@@B C EEGGIuJuLLNaOaQQSMTMVVX9Y9[[]%^%``bceeggisjslln_o_qqsKtKvvx7y7{{}#~#qq]]ӑӓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMWPMWPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM5.QMP5.QM;4QM,;4QMQMQMRM$RMyRMyRMSMSMтTMтTMTUMTUMIgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xf2 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 awB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xf2 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 awB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1xf2  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 awB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 (H b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1  } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>4?4IIS"T"^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGI\J\LLNJOJQQS8T8VVX&Y&[[]^``bceyeyggigjgllnPoPqqs4t4vvxy{{}}nnRRćĉ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOM_OML_OMOMTOM3OM3OMiOMiOMPM(PM1EPM1EPM{LPM{LPMVPM(VPM;YPM;YPMenPMenPMPMPMMPM MPM׿PM ׿PM PML  PMKPM KPMPM PMQM, QM+/QML+/QM5QM$5QM%QM%QMRMRMsRMsRMSMSMTMTMqTUMqTUMgUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1f  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 /++s b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations18&^ } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  QQ)=*=44>)?)IIST^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))wwc c""$O%O'');*;,,.'/'11346688:u;u==?a@aBBDMEMGGI9J9LLN!O!QQS T V}V}XXZe[e]]_M`Mbbd5e5ggijllnoqyqyssuavaxxzI{I}}11uu]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPM]PM]PMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM/.QMP/.QM7QM,7QMUQMUQMRM$RMgRMgRMSMSMwTMwTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zj6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 avB bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zj6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 avB bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1zj6  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 avB  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 <\ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1  bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1$-6?I } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  PP):*:44>&?&IIST^^hhrfsf} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffPP : :  $$mmW W""$A%A'')+*+,,./11335t6t88:^;^==?H@HBBD2E2GGIJLLNOQ}Q}SSUgVgXXZQ[Q]]_;`;bbd%e%ggijllnnphqhssuLvLxxz0{0}}jj܉܋NN22 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMǚOMǚOMeOMLeOMOMTOM3OM3OMiOMiOMPM(PM7EPM7EPM{LPM{LPMVPM(VPM;YPM;YPMknPMknPM PM PMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM8 QM/.QMX/.QMA4QM4A4QM׈QM׈QMRM,RMRMRMSMSM݂TM݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7MGoperation.3exchange :z2breasonOperatorInputsvalue7invocations1D@@ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1yrk } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  SS)A*A44>/?/IIST^^hisxsx} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeSS A A  //  p p""$^%^'')L*L,,.:/:113(4(6689;;=>@{@{BBDiEiGGIWJWLLNAOAQQS+T+VVXY[[]]_t`tbbd^e^ggiHjHlln2o2qqstvvxy{{{{}}eeڂڄOOćĉ99## b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMQPMQPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM5.QMP5.QMA4QM,A4QM=QM=QMRM$RMRMRMSMSMTMTMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m[' b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 aC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m[' b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 aC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m['  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 aC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ?n b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1@ bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1(<0p } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  ``)L*L44>8?8IIS T ^^his|s|} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll`` T T  HH<<00$$  "#%%'(*z*z,,.f/f113R4R668>9>;;=*>*@@BCEEGHJxJxLLN`O`QQSHTHVVX0Y0[[]^``bcetetggi\j\llnDoDqqs,t,vvxy{{}}ppXẊ̉@@(( b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMǚOMǚOMeOMLeOMOMTOM3OM3OMiOMiOMPM(PM7EPM7EPM{LPM{LPMVPM(VPM;YPM;YPMknPMknPM PM PMMPM MPM׿PM ׿PM PML  PMKPM KPMPM PMQM, QM+/QML+/QM5QM$5QMQMQMRMRMmRMmRMSMSMwTMwTMGTUMGTUMfUM } bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 @bC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 @bC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 @bC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b)goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 $  h b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b)goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r9_p16_c72_p72-:-z1211Z5ZYz]"]za"abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements648input0Elements648invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1d]VO } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  RR)<*<44>&?&IIS T ^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **xxd d""$O%O'')9*9,,.#/#113 4 6688:l;l==?V@VBBD@E@GGI*J*LLNOQQSSUiViXXZO[O]]_5`5bbdeggijltltnnpZqZssu@v@xxz&{&}} ee؉؋KK11 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations1l3OMOMOMOMLOMOMTOM3OM3OMiOMiOMPM(PMEPMEPM{LPM{LPMVPM(VPM;YPM;YPMnPMnPMQPMQPMMPM MPM׿PM ׿PM PML  PMOPM OPMPM PMQM0 QM5.QMP5.QM7QM,7QMQMQMRM$RMmRMmRMSMSMkTMkTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o_+ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.0exchange :z2breasonOperatorInputsvalue4invocations1 aC bwoperation.0ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue4kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.1ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue5bytes2304patternContiguousinvocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o_+ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7M7operation.1exchange :z2breasonOperatorInputsvalue5invocations1 aC bwoperation.1ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue5kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1  bWuoperation.2ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue6bytes2304patternContiguousinvocations1 } bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1o_+  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1 _ bJ7M7operation.2exchange :z2breasonOperatorInputsvalue6invocations1 aC  bwoperation.2ipu_stack_reduce_sum_f165:5z9299Z=2MzQ*QzU*UzY*Yb]reasonOperatorKernelvalue6kernelSpecPlanned(ReductionSum { partials: 2 })outputElements1152input0Elements1152input1Elements1152invocations1 bWuoperation.3ipu_stack_copy_u64%:%R)2))2)*)B)Z-b1reasonLocalCopyvalue7bytes2304patternContiguousinvocations1 b-goperation.3ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue7kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1 bJ7M7operation.3exchange :z2breasonOperatorInputsvalue7invocations1 ?_ b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1 b-goperation.4ipu_stack_unpack_amp_to_row_major_f16_o1_r16_p16_c72_p72-:-z1211Z5ZYz]*]za*abereasonOperatorKernelvalue8kernelSpecPlanned(Rearrange { from: Layout { order: Amp(TransposedLeft), tiling: TensorTiling { tile_count: 736, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 46, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 16, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: Some(46) }] }, memory_class: Ipu21Interleaved }, to: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard } })outputElements1152input0Elements1152invocations1Q bJ7Moperation.4exchange :z2breasonOperatorInputsvalue8invocations1 bJ7MWoperation.5exchange :z2breasonOperatorInputsvalue9invocations1Pdx D } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  ZZ)B*B44>*?*IIST^^hhrdsd} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jjZZ J J  ::**   ""$n%n'')V*V,,.>/>113&4&6689;;==?j@jBBDRERGGI:J:LLNOQQSTVtVtXXZX[X]]_<`v>xxz"{"}}xx\\Ή΋@@$$ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OMOMOMOMOMOM$OMPMPMOEPMOEPM{IPM${IPMnPMnPM!PM!PMMPM$MPM PM PMIPMIPM2QM 2QM̀QM| ̀QMRM RMRM RMSM SMтTM тTMTUMTUMIgUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14y& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14y& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14y& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10zz  jj)V*V44>>?>IIS&T&^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1zznn b b  VVJJ::&&  "#%%'')t*t,,.`/`113L4L668898;;=">"@@B C E~E~GGIfJfLLNNONQQS6T6VVXY[[]^`z`zbbdbebggiJjJlln2o2qqstvvxy{v{v}}^^҂҄FF++ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OM OM OMOM OM7OM7OMPMPMyEPMyEPM LPM LPMnPMpnPMKPMKPM۵PM۵PM PM` PMIPMIPM2QM2QM̀QML ̀QMRM RMyRMp yRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aO b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aO b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aO b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  ]])G*G44>-?-IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rr^^ J J  66""  l l""$V%V'')@*@,,.*/*11346688:s;s==?Y@YBBD?E?GGI%J%LLN O Q~Q~SSUdVdXXZJ[J]]_0`0bbdeggiikolonnpUqUssu;v;xxz!{!}}zz^^ЉЋBB&& b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OMߚOMߚOM}OM}OMOM$OMPMPMOEPMOEPM{IPM${IPMnPMnPM!PM!PMMPM$MPM PM PMIPMIPM2QM 2QM̀QM| ̀QMRM RMyRM yRMSM SMYTM YTM)TUM)TUMfUM} bJ7UGoperation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14w" b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7UGoperation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14w" b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7UGoperation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations14w" b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10xx  dd)L*L44>0?0IIST^^hhrhsh} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1xxhh X X  HH88$$   ""$h%h'')P*P,,.8/8113 4 6689;|;|==?`@`BBDDEDGGI(J(LLN O Q~Q~SSUbVbXXZF[F]]_*`*bbdeggiikdldnnpHqHssu,v,xxz{}}ff؄؆HH**  b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L?OMOMOMOM OM7OM7OMPMPMyEPMyEPM LPM LPMnPMpnPMKPMKPM۵PM۵PM PM` PMIPMIPM2QM2QM̀QML ̀QMRM RMgRMp gRMSMt SMTMT TMSUMSUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aQ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aQ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1aQ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  ]])C*C44>%?%IIST^x^xhhrXsX} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1tt`` L L  88$$  f f""$L%L'')2*2,,./11335q6q88:W;W==?9@9BBDEGGIIKnLnNNPPQPSSU2V2XXZ[]]__agbgddfIgIiik+l+nnp q s~s~uuw`x`zz|B}B$$ttTTĐĒ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMٚOMٚOMwOM wOMOMOMPMPMIEPMIEPM{IPM{IPM}nPMp}nPMPMPMMPMMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v# b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v# b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1v# b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10vv  hh)Z*Z44>J?JIIS6T6^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1vvhh Z Z  LL>>00""  "#%%'(**,,.q/q113c4c668U9U;;=G>G@@B9C9EEG+H+JJLMOOQRT~T~VVXlYl[[]Z^Z``bFcFeeg0h0jjlmooqrtstsvvxYyY{{}?~?%% {{__ёѓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMPMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMTUMTUM+gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jX$ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jX$ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jX$ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  ^^)H*H44>1?1IIST^^hisusu} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qqaa Q Q  AA11 } }""$g%g'')Q*Q,,.;/;113%4%6689;;==?n@nBBDXEXGGIAJALLN)O)QQSTVVXXZm[m]]_U`Ubbd=e=ggi%j%lln o qqssuivixxzQ{Q}}99!! ii b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMٚOMٚOMwOM wOMOMOMPMPMCEPMCEPM{IPM{IPMwnPMpwnPMPMPMMPMMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMRMp RMSMt SMTMT TMwTUMwTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1t b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10tt  bb)P*P44>>,,  ""$m%m'')[*[,,.I/I113747668%9%;;=>@@BCExExGGIdJdLLNNONQQS8T8VVX"Y"[[] ^ ``bbdgegggiMjMlln1o1qqstvvxxzf{f}}HH** ||^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L9OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPMQPMQPMPMPMPM`PMCPMCPM2QM2QM̀QML ̀QMRM RMsRMp sRMSMt SMqTMT qTMATUMATUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jZ& b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jZ& b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1jZ& b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10qq  \\)F*F44>.?.IIST^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1qq]] I I  55!!  k k""$U%U'')?*?,,.)/)11346688:r;r==?\@\BBDFEFGGI.J.LLNOQQSSUmVmXXZS[S]]_9`9bbdeggijlslsnnpWqWssu;v;xxz{}}uuYỶ̋??%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMӚOMӚOMqOM qOMOMOMPMPMCEPMCEPMIPMIPMwnPMpwnPMPMPMSPMSPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SM%TMT %TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 J} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 J} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 J  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10rr  bb)R*R44>@?@IIS,T,^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1rrbb R R  BB22""  "#%z%z'')j*j,,.Z/Z113J4J668:9:;;=*>*@@BCEEG H JJLLNlOlQQSXTXVVXDYD[[]0^0``bceeghj~j~llnjojqqsVtVvvxByB{{}.~.||hhޑޓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMׂTMT ׂTMTUMTUMOgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sa- b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1u} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sa- b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1u} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sa- b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1u  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  [[)I*I44>7?7IIS%T%^^h i s{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm[[ I I  77%% x x""$f%f'')T*T,,.B/B1130406689;;= > @@BBDqEqGGI_J_LLNMOMQQS;T;VVX)Y)[[]^``bce|e|ggijjjllnSoSqqs7t7vvxy{{}}qqUULJlj99 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMӚOMӚOMqOM qOMOMOMPMPM=EPM=EPMIPMIPMqnPMpqnPMPMPMSPMSPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMRMp RMSMt SMTMT TM}TUM}TUM%gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 K} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 K} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 K  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10pp  \\)H*H44>2?2IIST^^hisvsv} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1pp\\ H H  44    n n""$Z%Z'')F*F,,.2/21134668 9 ;;==?l@lBBDXEXGGIBJBLLN*O*QQSTVVXXZn[n]]_V`Vbbd>e>ggi&j&llnoqqssujvjxxzR{R}}::"" ~~ff b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMWPMWPMPMPMPM`PM=PM=PM1QM1QMǀQML ǀQMRM RMsRMp sRMSMt SM}TMT }TMMTUMMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sc/ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1u} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sc/ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1u} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1sc/ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1u  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  WW)A*A44>+?+IIST^^hhrksk} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmWW A A  ++tt^ ^""$H%H'')2*2,,./11346{6{88:e;e==?O@OBBD9E9GGI#J#LLN O QQSSUlVlXXZV[V]]_@`@bbd*e*ggijllnnpmqmssuQvQxxz5{5}}ooSSŎŐ77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OM͚OM͚OMkOM kOMOMOMPMPM=EPM=EPMoIPMoIPMqnPMpqnPMPMPMAPMAPMPM`PM=PM=PM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUM[gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1p b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  \\)J*J44>6?6IIS T ^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nn\\ J J  88&& y y""$g%g'')U*U,,.C/C1131416689;;= > @@BBDrErGGI^J^LLNHOHQQS2T2VVXY[[]^`{`{bbdeeeggiOjOlln9o9qqs#t#vvx y {{}}llVVˇˉ@@** b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPM]PM]PMPMPMPM`PM=PM=PM1QM1QMQML QMRM RMRMp RMSMt SM݂TMT ݂TMTUMTUMUgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|j6 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|j6 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|j6 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  aa)M*M44>7?7IIST^^his{s{} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmaa U U  II==11%%  "#%%'(*{*{,,.g/g113S4S668?9?;;=+>+@@BCEEGHJwJwLLN_O_QQSGTGVVX/Y/[[]^``bbdsesggi[j[llnCoCqqs+t+vvxy{{}}ooWWˇˉ??'' b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMoIPMoIPMknPMpknPM PM PMAPMAPMPM`PM=PM=PM1QM1QMQML QMRM RMmRMp mRMSMt SMwTMT wTMGTUMGTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1n b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  YY)C*C44>+?+IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mmYY E E  11  k k""$V%V'')@*@,,.*/*11346688:s;s==?]@]BBDGEGGGI/J/LLNOQQSSUnVnXXZT[T]]_:`:bbd e ggijlylynnp_q_ssuEvExxz+{+}}jj݉݋PPÎÐ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L3OMOMOMOM OMIOMIOMPMPMEPMEPMLPMLPMnPMpnPM]PM]PMPMPMPM`PM=PM=PM1QM1QMQML QMRM RMgRMp gRMSMt SMeTMT eTM5TUM5TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|l8 b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|l8 b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|l8 b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10mm  ]])E*E44>+?+IIST^^hhrese} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1mm]] M M  ==--   ""$q%q'')Y*Y,,.A/A113)4)6689;;==?m@mBBDUEUGGI;J;LLNOQQSTVuVuXXZY[Y]]_=`=bbd!e!ggijlwlwnnp[q[ssu?v?xxz#{#}}yy]]ωϋAA%% b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMǚOMǚOMeOM eOMOMOMPMPM7EPM7EPMIPMIPMknPMpknPM PM PMSPMSPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMTMT TMTUMTUM1gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1Q} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1Q} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1m b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1Q  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1c  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10nn  ^^)J*J44>2?2IIST^^histst} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1nnbb V V  JJ>>..  "#%|%|'')h*h,,.T/T113@4@668,9,;;=>@@BBDrErGGIZJZLLNBOBQQS*T*VVXY[[]]_n`nbbdVeVggi>j>lln&o&qqstvvxxzj{j}}RRƂƄ::xx b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OM!OM!OMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPM]PM]PMPMPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMYTMT YTM)TUM)TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1v} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1v} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1s? b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1v  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1\|  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  QQ);*;44>!?!IIST^z^zhhr^s^} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffRR > >  **vv` `""$J%J'')4*4,,./11346}6}88:g;g==?M@MBBD3E3GGIJLLNNPrQrSSUXVXXXZ>[>]]_$`$bbd e g}g}iikclcnnpIqIssu/v/xxz{}}nnRRĉċ66 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L-OMOMOM_OM _OMOMOMPMPM1EPM1EPM{IPM{IPMenPMpenPMPMPMMPMMPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMATMT ATMTUMTUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1P} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1P} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1k b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1P  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1t  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ll  XX)@*@44>$?$IIST^z^zhhr\s\} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ll\\ L L  <<,, t t""$\%\'')D*D,,.,/,11346688:p;p==?T@TBBD8E8GGIJLLNOQrQrSSUVVVXXZ:[:]]_`bbdegtgtiikXlXnnp?IISS]l^lhhrLsL} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhTT @ @  ,,ttZ Z""$@%@'')&*&,,. / 11335e6e88:K;K==?-@-BBDEGGIIKbLbNNPDQDSSU&V&XXZ[]y]y__a[b[ddf=g=iiklnnpqsrsruuwTxTzz|6}6hh؋؍HH b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOM_OM _OMOMOMPMPM+EPM+EPMiIPMiIPM_nPMp_nPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMRMp RMSMt SMTMT TMTUMTUMygUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1j b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10jj  \\)N*N44>>?>IIS*T*^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1jj\\ N N  @@22$$  "#%%'')s*s,,.e/e113W4W668I9I;;=;>;@@B-C-EEGHJJL M OOQQSrTrVVX`Y`[[]N^N``b:c:eeg$h$jjlmooqqsgtgvvxMyM{{}3~3ooSSőœ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM'OM'OMOM OM=OM=OMPMPMEPMEPMLPMLPMnPMpnPMcPMcPMPMPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1|H b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1a  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  RR)<*<44>%?%IIS T ^^hhrisi} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeUU E E  55%%q q""$[%['')E*E,,.///11346689;x;x==?b@bBBDLELGGI5J5LLNOQQSTVyVyXXZa[a]]_I`Ibbd1e1ggijllnoququssu]v]xxzE{E}}--ss]] b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOMOMOMPMPM+EPM+EPMiIPMiIPM_nPMp_nPMPMPM;PM;PMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TM_TUM_TUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1h b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10hh  VV)D*D44>0?0IIST^^hhrjsj} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1hhVV D D  22  s s""$a%a'')O*O,,.=/=113+4+6689;;=>@~@~BBDlElGGIXJXLLNBOBQQS,T,VVXY[[]^`u`ubbd[e[ggiAjAlln%o%qqstvxvxxxzZ{Z}}<<ppRR b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM'OM'OMOM OM=OM=OMPMPMEPMEPMLPMLPMnPMpnPMiPMiPMPMPMPM`PMQMQM1QM1QMQML QMRM RM[RMp [RMSMt SMSTMT STM#TUM#TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1~J b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1z  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ee  PP):*:44>"?"IIST^y^yhhr]s]} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1eeQQ = =  ))uu_ _""$I%I'')3*3,,./11346|6|88:f;f==?P@PBBD:E:GGI"J"LLNOQ{Q{SSUaVaXXZG[G]]_-`-bbdeggiikglgnnpKqKssu/v/xxz{}}iiۄۆMM33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMYOM YOMOMOMPMPM%EPM%EPMuIPMuIPMYnPMpYnPMPMPMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMyRMp yRMSMt SM TMT  TMTUMTUMgUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1N} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1N} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1g b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1N  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1o  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10ff  VV)F*F44>4?4IIS T ^^hiss} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ffVV F F  66&& ~ ~""$n%n'')^*^,,.N/N113>4>668.9.;;=>@@BCEEGGItJtLLN`O`QQSLTLVVX8Y8[[]$^$``bceeggirjrlln`o`qqsLtLvvx8y8{{}$~$rr^^ԑԓ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM'OM'OMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMiPMiPMPMPMPM`PMQMQM1QM1QMQML QMRM RMsRMp sRMSMt SMłTMT łTMTUMTUM=gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1u} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1u} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Q b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1u  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1h  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  OO)=*=44>+?+IIST^^hisysy} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaOO = =  ++~~l l""$Z%Z'')H*H,,.6/6113$4$6689;;=>@w@wBBDeEeGGISJSLLNAOAQQS/T/VVXY[[] ^ ``bbdpepggi^j^llnQoQqqs5t5vvxy{{}}ooSSŇʼn77 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OMOMOMSOM SOMOMOMPMPM%EPM%EPMuIPMuIPMYnPMpYnPMPMPMGPMGPMPM`PMQMQM1QM1QMQML QMRM RMgRMp gRMSMt SMTMT TMeTUMeTUM gUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1 M} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1 M} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1e b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1 M  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10dd  PP)<*<44>&?&IIST^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1ddPP < <  ((vvb b""$N%N''):*:,,.&/&11346688:t;t==?`@`BBDLELGGI6J6LLNOQQSTVzVzXXZb[b]]_J`Jbbd2e2ggijllnoqzqzssubvbxxzJ{J}}22vv^^ b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L'OM-OM-OMOM OMOMOMPMPMEPMEPMKPMKPMnPMpnPMiPMiPMPMPMPM`PMQMQM1QM1QMQML QMRM RMaRMp aRMSMt SMkTMT kTM;TUM;TUMfUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1u} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1u} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1S b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1u  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r8_p8_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements576input0Elements576invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  KK)5*544>?IIS T ^^hhrgsg} b)woperation.6ipu_stack_gemm_f16_init_large_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements6144input0Elements576input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_large_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements6272input0Elements6144invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaKK 5 5    ~~hhR R""$<%<'')&*&,,./11335o6o88:Y;Y==?C@CBBD-E-GGIJLLNOQvQvSSU`V`XXZJ[J]]_4`4bbdeggijl}l}nnpiqissuMvMxxz1{1}}kk݉݋OO33 b)woperation.6ipu_stack_gemm_f16_init_large_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements640input0Elements6144input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_large_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements576input0Elements640input1Elements6272invocations17L!OMOMOMMOM MOMOMOMPMPMEPMEPMcIPMcIPMSnPMpSnPMPMPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMтTMT тTMRUMRUMoeUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1d b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10bb  PP)@*@44>,?,IIST^^h i ss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1bbPP > >  ,,m m""$]%]'')K*K,,.9/9113'4'6689;;=>@z@zBBDhEhGGITJTLLN>O>QQS(T(VVXY[[]]_q`qbbd[e[ggiEjElln;o;qqs%t%vvxy{{}}nnXX͇͉BB,, b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM-OM-OMOM OM1OM1OMPMPMEPMEPMLPMLPMnPMpnPMoPMoPMյPMյPMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMׂTMT ׂTMRUMRUMueUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1Z b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  UU)K*K44>5?5IIST^^hiss} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaUU I I  ==11%%  " # %%'(*y*y,,.e/e113Q4Q668=9=;;=)>)@@BCEEGHJuJuLLN]O]QQSETEVVX-Y-[[]^``bbdqeqggiYjYllnMoMqqs5t5vvxy{{}~yyaaՇՉII11 b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OMOMOMMOM MOMOMOM{PM{PMEPMEPMcIPMcIPMMnPMpMnPMPMPM5PM5PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SMkTMT kTMaRUMaRUM eUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1@} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1@} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1b  b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}"}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements648input0Elements41472input1Elements5184invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1@  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  MM);*;44>#?#IIS T ^^hhrnsn} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaMM 9 9  %%ss_ _""$N%N'')8*8,,."/"113 4 6688:k;k==?U@UBBD?E?GGI'J'LLN O QQSSUfVfXXZL[L]]_2`2bbdeggiikqlqnnpcqcssuIvIxxz/{/}}nnTTǎǐ:: b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations17L!OM3OM3OMOM OM7OM7OMPMPMEPMEPM LPM LPMnPMpnPMoPMoPM۵PM۵PMPM`PMPMPM1QM1QMQML QMRM RMRMp RMSMt SM_TMT _TMURUMURUMdUM} bJ7U'operation.0exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.0ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue4kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.0exchange :z2breasonOperatorInputsvalue4invocations1} bJ7U'operation.1exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.1ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue5kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.1exchange :z2breasonOperatorInputsvalue5invocations1} bJ7U'operation.2exchange :!2!!b%reasonOperatorInput { input: 0 }value0invocations1\ b-woperation.2ipu_stack_gemm_f16_init_small_rows_interleaved_k576_c16_r72_r725:5z9299Z=yz}*}z2z*breasonOperatorKernelvalue6kernelSpecPlanned(Gemm { multiply: F16, accumulate: F16, mode: Initialize, weights: Interleaved, inner_block: 576, output_columns: 16 })outputElements1152input0Elements41472input1Elements9216invocations1_ bJ7Moperation.2exchange :z2breasonOperatorInputsvalue6invocations1  bJ7Moperation.3exchange :z2breasonOperatorInputsvalue7invocations1  b-g operation.3ipu_stack_rearrange_row_major_to_amp_f16_o0_r7_p7_c72_p80-:-z1211Z5z"z"breasonOperatorInputsvalue7kernelSpecPlanned(Rearrange { from: Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1, replicas: 1, axes: [] }, memory_class: Ipu21Standard }, to: Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1472, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 92, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(16) }, AxisTiling { axis: FromEnd(3), partitions: 16, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: Some(1) }, AxisTiling { axis: FromEnd(1), partitions: 1, block_size: 16, padding_multiple: 16, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } })outputElements504input0Elements504invocations1  b*7Ioperation.4sync :2breasonExchangeBarriervalue8invocations1  b*7Ioperation.5sync :2breasonExchangeBarriervalue9invocations1 } bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations10aa  QQ)A*A44>'?'IIS T ^^hhrmsm} b)woperation.6ipu_stack_gemm_f16_init_small_rows_k80_c768_r7_r85:5z9299Z=yz}*}z"z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 80, output_columns: 768 })outputElements5376input0Elements504input1Elements52488invocations1 b)goperation.6ipu_stack_attention_softmax_small_query_small_key_f16-:-z1211Z5aze*ezi*ibmreasonOperatorKernelvalue10kernelSpecPlanned(AttentionSoftmax { head_dimension: 72, key_columns: 729, padded_key_columns: 768 })outputElements5488input0Elements5376invocations1 bJ7Moperation.6exchange :z2breasonOperatorInputsvalue8invocations1aaQQ A A  11!! y y""$m%m'')U*U,,.=/=113%4%668 9 ;;==?i@iBBDQEQGGI7J7LLNOQQSSUqVqXXZU[U]]_9`9bbdeggijlslsnnpcqcssuGvGxxz+{+}}ee׉׋II-- b)woperation.6ipu_stack_gemm_f16_init_small_rows_k768_c80_r7_r85:5z9299Z=yz}"}z*z2breasonOperatorKernelvalue10kernelSpecPlanned(Gemm { multiply: F16, accumulate: F32, mode: Initialize, weights: Standard, inner_block: 768, output_columns: 80 })outputElements560input0Elements5376input1Elements52488invocations1 bR%woperation.6ipu_stack_attention_merge_small_query_f165:5z9299Z=2}z"z"z*breasonOperatorKernelvalue10kernelSpecPlanned(AttentionMerge { value_dimension: 72, padded_value_dimension: 80, key_block_columns: 768, initial: true, final_block: true })outputElements504input0Elements560input1Elements5488invocations1