2026-09-13T09:31:31.771527Z DEBUG priced residual/statistics fusion source=Some(OperationId(17)) parts=2 redistributed=true before=Some(8211) after=Some(8632) 2026-09-13T09:31:31.771614Z DEBUG considering direct FP8 output producer=Some(OperationId(25)) consumer=Some(OperationId(26)) kernel=LayerNorm input_layout=Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1458, replicas: 18, axes: [AxisTiling { axis: FromEnd(1), partitions: 9, padding_groups: 1, block_size: 128, padding_multiple: 128, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 9, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } output_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1458, replicas: 18, axes: [AxisTiling { axis: FromEnd(1), partitions: 9, padding_groups: 1, block_size: 128, padding_multiple: 128, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 9, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } 2026-09-13T09:31:31.771724Z DEBUG considering direct FP8 output producer=Some(OperationId(42)) consumer=Some(OperationId(43)) kernel=Gelu input_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1440, replicas: 72, axes: [AxisTiling { axis: FromEnd(1), partitions: 20, padding_groups: 1, block_size: 224, padding_multiple: 224, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 1, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } output_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1440, replicas: 72, axes: [AxisTiling { axis: FromEnd(1), partitions: 20, padding_groups: 1, block_size: 224, padding_multiple: 224, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 1, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } 2026-09-13T09:31:31.771763Z DEBUG considering direct FP8 output producer=Some(OperationId(3)) consumer=Some(OperationId(4)) kernel=LayerNorm input_layout=Layout { order: RowMajor, tiling: TensorTiling { tile_count: 183, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 183, padding_groups: 1, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: None }] }, memory_class: Ipu21Standard } output_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 183, replicas: 1, axes: [AxisTiling { axis: FromEnd(2), partitions: 183, padding_groups: 1, block_size: 1, padding_multiple: 1, shard_padding_multiple: 1, padding: Reject, tile_stride: None }] }, memory_class: Ipu21Standard } 2026-09-13T09:31:31.771925Z DEBUG considering direct FP8 output producer=Some(OperationId(17)) consumer=Some(OperationId(18)) kernel=LayerNorm input_layout=Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1458, replicas: 27, axes: [AxisTiling { axis: FromEnd(1), partitions: 6, padding_groups: 1, block_size: 192, padding_multiple: 192, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 9, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } output_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1458, replicas: 27, axes: [AxisTiling { axis: FromEnd(1), partitions: 6, padding_groups: 1, block_size: 192, padding_multiple: 192, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 9, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } 2026-09-13T09:31:31.771973Z DEBUG considering direct FP8 output producer=Some(OperationId(20)) consumer=Some(OperationId(21)) kernel=Gelu input_layout=Layout { order: RowMajor, tiling: TensorTiling { tile_count: 1458, replicas: 9, axes: [AxisTiling { axis: FromEnd(1), partitions: 27, padding_groups: 1, block_size: 160, padding_multiple: 160, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 6, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } output_layout=Layout { order: Amp(Left), tiling: TensorTiling { tile_count: 1458, replicas: 9, axes: [AxisTiling { axis: FromEnd(1), partitions: 27, padding_groups: 1, block_size: 160, padding_multiple: 160, shard_padding_multiple: 1, padding: Zero, tile_stride: None }, AxisTiling { axis: FromEnd(2), partitions: 6, padding_groups: 1, block_size: 2, padding_multiple: 2, shard_padding_multiple: 1, padding: Zero, tile_stride: None }] }, memory_class: Ipu21Standard } exchangeRows=87770 counts=[send, sendoff, sendpic, sendpicp, standaloneControl, unknown]=[1426181, 293281, 1534712, 135426, 4015213, 5502] longest=[(658, 2691, 26, 424328, [244, 0, 239, 8, 63, 0]), (645, 2689, 722, 424632, [244, 1, 225, 8, 63, 0]), (644, 14498, 1408, 411496, [38, 22, 50, 172, 148, 0]), (644, 14497, 1410, 411616, [38, 24, 55, 172, 142, 0]), (644, 2694, 671, 425232, [244, 2, 221, 7, 69, 0]), (639, 14498, 384, 411552, [38, 12, 24, 203, 111, 0]), (638, 14494, 1409, 411488, [38, 18, 51, 176, 136, 0]), (637, 14618, 390, 411400, [38, 30, 19, 216, 83, 0]), (637, 14617, 388, 411400, [38, 32, 19, 216, 84, 0]), (637, 14497, 386, 411520, [38, 11, 15, 203, 120, 0]), (636, 14495, 1411, 411504, [38, 16, 51, 172, 146, 0]), (636, 2687, 182, 421864, [238, 2, 217, 11, 66, 0]), (633, 14623, 387, 411616, [38, 14, 13, 216, 92, 0]), (633, 14622, 385, 411584, [38, 12, 9, 216, 95, 0]), (630, 2677, 878, 422008, [238, 1, 237, 5, 51, 0]), (628, 12443, 387, 418248, [77, 37, 72, 77, 264, 0])]