96 lines
3.5 KiB
Plaintext
96 lines
3.5 KiB
Plaintext
README.md
|
|
setup.py
|
|
vllm_mlu/__init__.py
|
|
vllm_mlu/_mlu_utils.py
|
|
vllm_mlu/config.py
|
|
vllm_mlu/dump_info.py
|
|
vllm_mlu/mlu_hijack.py
|
|
vllm_mlu/mlu_hijack_utils.py
|
|
vllm_mlu/mlu_metric.py
|
|
vllm_mlu/utils.py
|
|
vllm_mlu.egg-info/PKG-INFO
|
|
vllm_mlu.egg-info/SOURCES.txt
|
|
vllm_mlu.egg-info/dependency_links.txt
|
|
vllm_mlu.egg-info/top_level.txt
|
|
vllm_mlu/attention/__init__.py
|
|
vllm_mlu/attention/layer.py
|
|
vllm_mlu/attention/selector.py
|
|
vllm_mlu/attention/backends/__init__.py
|
|
vllm_mlu/attention/backends/mlu_attn.py
|
|
vllm_mlu/attention/ops/__init__.py
|
|
vllm_mlu/attention/ops/prefix_prefill.py
|
|
vllm_mlu/attention/ops/triton_flash_attention.py
|
|
vllm_mlu/core/__init__.py
|
|
vllm_mlu/core/block_manager.py
|
|
vllm_mlu/core/scheduler.py
|
|
vllm_mlu/distributed/__init__.py
|
|
vllm_mlu/distributed/parallel_state.py
|
|
vllm_mlu/engine/__init__.py
|
|
vllm_mlu/engine/arg_utils.py
|
|
vllm_mlu/engine/async_llm_engine.py
|
|
vllm_mlu/engine/llm_engine.py
|
|
vllm_mlu/engine/multiprocessing/__init__.py
|
|
vllm_mlu/engine/multiprocessing/client.py
|
|
vllm_mlu/engine/multiprocessing/engine.py
|
|
vllm_mlu/entrypoints/__init__.py
|
|
vllm_mlu/entrypoints/llm.py
|
|
vllm_mlu/entrypoints/openai/__init__.py
|
|
vllm_mlu/entrypoints/openai/serving_engine.py
|
|
vllm_mlu/executor/__init__.py
|
|
vllm_mlu/executor/mlu_executor.py
|
|
vllm_mlu/executor/multiproc_mlu_executor.py
|
|
vllm_mlu/executor/ray_mlu_executor.py
|
|
vllm_mlu/lora/__init__.py
|
|
vllm_mlu/lora/fully_sharded_layers.py
|
|
vllm_mlu/lora/layers.py
|
|
vllm_mlu/lora/punica.py
|
|
vllm_mlu/lora/ops/__init__.py
|
|
vllm_mlu/lora/ops/sgmv_expand.py
|
|
vllm_mlu/lora/ops/sgmv_expand_slice.py
|
|
vllm_mlu/lora/ops/sgmv_shrink.py
|
|
vllm_mlu/lora/ops/utils.py
|
|
vllm_mlu/model_executor/__init__.py
|
|
vllm_mlu/model_executor/custom_model/__init__.py
|
|
vllm_mlu/model_executor/custom_model/custom.py
|
|
vllm_mlu/model_executor/layers/__init__.py
|
|
vllm_mlu/model_executor/layers/activation.py
|
|
vllm_mlu/model_executor/layers/feed_forward.py
|
|
vllm_mlu/model_executor/layers/linear.py
|
|
vllm_mlu/model_executor/layers/rotary_embedding.py
|
|
vllm_mlu/model_executor/layers/sparse_moe_mlp.py
|
|
vllm_mlu/model_executor/layers/spec_decode_base_sampler.py
|
|
vllm_mlu/model_executor/layers/quantization/__init__.py
|
|
vllm_mlu/model_executor/layers/quantization/awq_mlu.py
|
|
vllm_mlu/model_executor/layers/quantization/gptq_mlu.py
|
|
vllm_mlu/model_executor/layers/quantization/smoothquant.py
|
|
vllm_mlu/model_executor/layers/quantization/weightonly.py
|
|
vllm_mlu/model_executor/model_loader/__init__.py
|
|
vllm_mlu/model_executor/model_loader/loader.py
|
|
vllm_mlu/model_executor/model_loader/tensorizer.py
|
|
vllm_mlu/model_executor/models/__init__.py
|
|
vllm_mlu/model_executor/models/baichuan.py
|
|
vllm_mlu/model_executor/models/bloom.py
|
|
vllm_mlu/model_executor/models/chatglm.py
|
|
vllm_mlu/model_executor/models/clip.py
|
|
vllm_mlu/model_executor/models/deepseek_v2.py
|
|
vllm_mlu/model_executor/models/falcon.py
|
|
vllm_mlu/model_executor/models/gpt_neox.py
|
|
vllm_mlu/model_executor/models/hunyuan.py
|
|
vllm_mlu/model_executor/models/internlm2.py
|
|
vllm_mlu/model_executor/models/layer_utils.py
|
|
vllm_mlu/model_executor/models/llama.py
|
|
vllm_mlu/model_executor/models/mixtral.py
|
|
vllm_mlu/model_executor/models/mllama.py
|
|
vllm_mlu/model_executor/models/qwen.py
|
|
vllm_mlu/model_executor/models/qwen2.py
|
|
vllm_mlu/model_executor/models/qwen2_moe.py
|
|
vllm_mlu/model_executor/models/qwen2_vl.py
|
|
vllm_mlu/transformers_utils/__init__.py
|
|
vllm_mlu/transformers_utils/configs/__init__.py
|
|
vllm_mlu/transformers_utils/configs/custom.py
|
|
vllm_mlu/worker/__init__.py
|
|
vllm_mlu/worker/cache_engine.py
|
|
vllm_mlu/worker/mlu_enc_dec_model_runner.py
|
|
vllm_mlu/worker/mlu_model_runner.py
|
|
vllm_mlu/worker/mlu_multi_step_model_runner.py
|
|
vllm_mlu/worker/mlu_worker.py |