Index of /gc-sdk/vllm-fork/examples/

NameSizeLast Modified
../-
api_client.py2.7kB2026-02-14 16:46:53
aqlm_example.py1.5kB2026-02-14 16:46:53
cpu_offload.py763 B2026-02-14 16:46:53
fp8/-2026-02-14 16:46:53
gguf_inference.py1.4kB2026-02-14 16:46:53
gradio_openai_chatbot_webserver.py2.8kB2026-02-14 16:46:53
gradio_webserver.py1.6kB2026-02-14 16:46:53
llm_engine_example.py2.3kB2026-02-14 16:46:53
logging_configuration.md5.5kB2026-02-14 16:46:53
lora_with_quantization_inference.py5.0kB2026-02-14 16:46:53
multilora_inference.py5.7kB2026-02-14 16:46:53
offline_inference.py731 B2026-02-14 16:46:53
offline_inference_arctic.py856 B2026-02-14 16:46:53
offline_inference_audio_language.py3.4kB2026-02-14 16:46:53
offline_inference_chat.py1.3kB2026-02-14 16:46:53
offline_inference_distributed.py3.6kB2026-02-14 16:46:53
offline_inference_embedding.py480 B2026-02-14 16:46:53
offline_inference_encoder_decoder.py3.3kB2026-02-14 16:46:53
offline_inference_mlpspeculator.py1.8kB2026-02-14 16:46:53
offline_inference_neuron.py1.6kB2026-02-14 16:46:53
offline_inference_neuron_int8_quantization.py1.9kB2026-02-14 16:46:53
offline_inference_openai.md10.1kB2026-02-14 16:46:53
offline_inference_tpu.py1.1kB2026-02-14 16:46:53
offline_inference_vision_language.py7.2kB2026-02-14 16:46:53
offline_inference_vision_language_multi_image.py5.1kB2026-02-14 16:46:53
offline_inference_with_prefix.py2.9kB2026-02-14 16:46:53
offline_inference_with_profiler.py896 B2026-02-14 16:46:53
openai_audio_api_client.py2.3kB2026-02-14 16:46:53
openai_chat_completion_client.py868 B2026-02-14 16:46:53
openai_chat_completion_client_with_tools.py5.2kB2026-02-14 16:46:53
openai_completion_client.py660 B2026-02-14 16:46:53
openai_embedding_client.py615 B2026-02-14 16:46:53
openai_example_batch.jsonl551 B2026-02-14 16:46:53
openai_vision_api_client.py3.6kB2026-02-14 16:46:53
production_monitoring/-2026-02-14 16:46:53
run_cluster.sh1.3kB2026-02-14 16:46:53
save_sharded_state.py2.5kB2026-02-14 16:46:53
template_alpaca.jinja667 B2026-02-14 16:46:53
template_baichuan.jinja524 B2026-02-14 16:46:53
template_blip2.jinja332 B2026-02-14 16:46:53
template_chatglm.jinja629 B2026-02-14 16:46:53
template_chatglm2.jinja637 B2026-02-14 16:46:53
template_chatml.jinja316 B2026-02-14 16:46:53
template_falcon.jinja471 B2026-02-14 16:46:53
template_falcon_180b.jinja558 B2026-02-14 16:46:53
template_inkbot.jinja1.0kB2026-02-14 16:46:53
template_llava.jinja766 B2026-02-14 16:46:53
tensorize_vllm_model.py9.1kB2026-02-14 16:46:53
tool_chat_template_hermes.jinja5.2kB2026-02-14 16:46:53
tool_chat_template_mistral.jinja4.0kB2026-02-14 16:46:53
tool_chat_template_mistral_parallel.jinja4.8kB2026-02-14 16:46:53