add qwen3

2026-02-04 17:22:39 +08:00
parent d1c0f68ab4
commit 8511fe8530
1932 changed files with 300426 additions and 0 deletions
--- a/vllm-v0.6.2/vllm.egg-info/PKG-INFO
+++ b/vllm-v0.6.2/vllm.egg-info/PKG-INFO
@@ -0,0 +1,227 @@
+Metadata-Version: 2.2
+Name: vllm
+Version: 0.6.4.post1+mlu0.6.2.pt2.5
+Summary: A high-throughput and memory-efficient inference and serving engine for LLMs on MLU backendon
+Home-page: 
+Author: Cambricon vLLM Team
+License: Apache 2.0
+Project-URL: Homepage, https://github.com/vllm-project/vllm
+Project-URL: Documentation, https://vllm.readthedocs.io/en/latest/
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: psutil
+Requires-Dist: sentencepiece
+Requires-Dist: numpy<2.0.0
+Requires-Dist: requests>=2.26.0
+Requires-Dist: tqdm
+Requires-Dist: py-cpuinfo
+Requires-Dist: transformers>=4.45.2
+Requires-Dist: tokenizers>=0.19.1
+Requires-Dist: protobuf
+Requires-Dist: fastapi<0.113.0,>=0.107.0; python_version < "3.9"
+Requires-Dist: fastapi!=0.113.*,!=0.114.0,>=0.107.0; python_version >= "3.9"
+Requires-Dist: aiohttp
+Requires-Dist: openai>=1.45.0
+Requires-Dist: uvicorn[standard]
+Requires-Dist: pydantic>=2.9
+Requires-Dist: pillow
+Requires-Dist: prometheus_client>=0.18.0
+Requires-Dist: prometheus-fastapi-instrumentator>=7.0.0
+Requires-Dist: tiktoken>=0.6.0
+Requires-Dist: lm-format-enforcer<0.11,>=0.10.9
+Requires-Dist: outlines<0.1,>=0.0.43
+Requires-Dist: typing_extensions>=4.10
+Requires-Dist: filelock>=3.10.4
+Requires-Dist: partial-json-parser
+Requires-Dist: pyzmq
+Requires-Dist: msgspec
+Requires-Dist: gguf==0.10.0
+Requires-Dist: importlib_metadata
+Requires-Dist: mistral_common[opencv]>=1.5.0
+Requires-Dist: pyyaml
+Requires-Dist: six>=1.16.0; python_version > "3.11"
+Requires-Dist: setuptools>=74.1.1; python_version > "3.11"
+Requires-Dist: einops
+Requires-Dist: compressed-tensors==0.8.0
+Requires-Dist: tensorizer
+Requires-Dist: matplotlib>=3.7.4
+Requires-Dist: accelerate
+Requires-Dist: loguru
+Requires-Dist: ray==2.40.0
+Requires-Dist: triton==3.0.0
+Requires-Dist: torch==2.5.0
+Requires-Dist: torch-mlu>=1.23.1
+Requires-Dist: torch_mlu_ops>=1.2.2
+Requires-Dist: xformers==0.0.24
+Requires-Dist: datasets
+Requires-Dist: transformers_stream_generator
+Requires-Dist: huggingface-hub==0.25.2
+Provides-Extra: tensorizer
+Requires-Dist: tensorizer>=2.9.0; extra == "tensorizer"
+Provides-Extra: audio
+Requires-Dist: librosa; extra == "audio"
+Requires-Dist: soundfile; extra == "audio"
+Provides-Extra: video
+Requires-Dist: decord; extra == "video"
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/logos/vllm-logo-text-dark.png">
+    <img alt="vLLM" src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/source/assets/logos/vllm-logo-text-light.png" width=55%>
+  </picture>
+</p>
+
+<h3 align="center">
+Easy, fast, and cheap LLM serving for everyone
+</h3>
+
+<p align="center">
+| <a href="https://docs.vllm.ai"><b>Documentation</b></a> | <a href="https://vllm.ai"><b>Blog</b></a> | <a href="https://arxiv.org/abs/2309.06180"><b>Paper</b></a> | <a href="https://discord.gg/jz7wjKhh6g"><b>Discord</b></a> | <a href="https://x.com/vllm_project"><b>Twitter/X</b></a> |
+
+</p>
+
+
+---
+
+**vLLM, AMD, Anyscale Meet & Greet at [Ray Summit 2024](http://raysummit.anyscale.com) (Monday, Sept 30th, 5-7pm PT) at Marriott Marquis San Francisco**
+
+We are excited to announce our special vLLM event in collaboration with AMD and Anyscale.
+Join us to learn more about recent advancements of vLLM on MI300X.
+Register [here](https://lu.ma/db5ld9n5) and be a part of the event!
+
+---
+
+*Latest News* 🔥
+- [2024/09] We hosted [the sixth vLLM meetup](https://lu.ma/87q3nvnh) with NVIDIA! Please find the meetup slides [here](https://docs.google.com/presentation/d/1wrLGwytQfaOTd5wCGSPNhoaW3nq0E-9wqyP7ny93xRs/edit?usp=sharing).
+- [2024/07] We hosted [the fifth vLLM meetup](https://lu.ma/lp0gyjqr) with AWS! Please find the meetup slides [here](https://docs.google.com/presentation/d/1RgUD8aCfcHocghoP3zmXzck9vX3RCI9yfUAB2Bbcl4Y/edit?usp=sharing).
+- [2024/07] In partnership with Meta, vLLM officially supports Llama 3.1 with FP8 quantization and pipeline parallelism! Please check out our blog post [here](https://blog.vllm.ai/2024/07/23/llama31.html).
+- [2024/06] We hosted [the fourth vLLM meetup](https://lu.ma/agivllm) with Cloudflare and BentoML! Please find the meetup slides [here](https://docs.google.com/presentation/d/1iJ8o7V2bQEi0BFEljLTwc5G1S10_Rhv3beed5oB0NJ4/edit?usp=sharing).
+- [2024/04] We hosted [the third vLLM meetup](https://robloxandvllmmeetup2024.splashthat.com/) with Roblox! Please find the meetup slides [here](https://docs.google.com/presentation/d/1A--47JAK4BJ39t954HyTkvtfwn0fkqtsL8NGFuslReM/edit?usp=sharing).
+- [2024/01] We hosted [the second vLLM meetup](https://lu.ma/ygxbpzhl) with IBM! Please find the meetup slides [here](https://docs.google.com/presentation/d/12mI2sKABnUw5RBWXDYY-HtHth4iMSNcEoQ10jDQbxgA/edit?usp=sharing).
+- [2023/10] We hosted [the first vLLM meetup](https://lu.ma/first-vllm-meetup) with a16z! Please find the meetup slides [here](https://docs.google.com/presentation/d/1QL-XPFXiFpDBh86DbEegFXBXFXjix4v032GhShbKf3s/edit?usp=sharing).
+- [2023/08] We would like to express our sincere gratitude to [Andreessen Horowitz](https://a16z.com/2023/08/30/supporting-the-open-source-ai-community/) (a16z) for providing a generous grant to support the open-source development and research of vLLM.
+- [2023/06] We officially released vLLM! FastChat-vLLM integration has powered [LMSYS Vicuna and Chatbot Arena](https://chat.lmsys.org) since mid-April. Check out our [blog post](https://vllm.ai).
+
+---
+## About
+vLLM is a fast and easy-to-use library for LLM inference and serving.
+
+vLLM is fast with:
+
+- State-of-the-art serving throughput
+- Efficient management of attention key and value memory with **PagedAttention**
+- Continuous batching of incoming requests
+- Fast model execution with CUDA/HIP graph
+- Quantizations: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), INT4, INT8, and FP8.
+- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer.
+- Speculative decoding
+- Chunked prefill
+
+**Performance benchmark**: We include a [performance benchmark](https://buildkite.com/vllm/performance-benchmark/builds/4068) that compares the performance of vLLM against other LLM serving engines ([TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [text-generation-inference](https://github.com/huggingface/text-generation-inference) and [lmdeploy](https://github.com/InternLM/lmdeploy)).
+
+vLLM is flexible and easy to use with:
+
+- Seamless integration with popular Hugging Face models
+- High-throughput serving with various decoding algorithms, including *parallel sampling*, *beam search*, and more
+- Tensor parallelism and pipeline parallelism support for distributed inference
+- Streaming outputs
+- OpenAI-compatible API server
+- Support NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs and GPUs, PowerPC CPUs, TPU, and AWS Neuron.
+- Prefix caching support
+- Multi-lora support
+
+vLLM seamlessly supports most popular open-source models on HuggingFace, including:
+- Transformer-like LLMs (e.g., Llama)
+- Mixture-of-Expert LLMs (e.g., Mixtral)
+- Embedding Models (e.g. E5-Mistral)
+- Multi-modal LLMs (e.g., LLaVA)
+
+Find the full list of supported models [here](https://docs.vllm.ai/en/latest/models/supported_models.html).
+
+## Getting Started
+
+Install vLLM with `pip` or [from source](https://vllm.readthedocs.io/en/latest/getting_started/installation.html#build-from-source):
+
+```bash
+pip install vllm
+```
+
+Visit our [documentation](https://vllm.readthedocs.io/en/latest/) to learn more.
+- [Installation](https://vllm.readthedocs.io/en/latest/getting_started/installation.html)
+- [Quickstart](https://vllm.readthedocs.io/en/latest/getting_started/quickstart.html)
+- [Supported Models](https://vllm.readthedocs.io/en/latest/models/supported_models.html)
+
+## Contributing
+
+We welcome and value any contributions and collaborations.
+Please check out [CONTRIBUTING.md](./CONTRIBUTING.md) for how to get involved.
+
+## Sponsors
+
+vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!
+
+<!-- Note: Please sort them in alphabetical order. -->
+<!-- Note: Please keep these consistent with docs/source/community/sponsors.md -->
+
+- a16z
+- AMD
+- Anyscale
+- AWS
+- Crusoe Cloud
+- Databricks
+- DeepInfra
+- Dropbox
+- Google Cloud
+- Lambda Lab
+- NVIDIA
+- Replicate
+- Roblox
+- RunPod
+- Sequoia Capital
+- Skywork AI
+- Trainy
+- UC Berkeley
+- UC San Diego
+- ZhenFund
+
+We also have an official fundraising venue through [OpenCollective](https://opencollective.com/vllm). We plan to use the fund to support the development, maintenance, and adoption of vLLM.
+
+## Citation
+
+If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs/2309.06180):
+```bibtex
+@inproceedings{kwon2023efficient,
+  title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
+  author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica},
+  booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
+  year={2023}
+}
+```
+
+## Contact Us
+
+* For technical questions and feature requests, please use Github issues or discussions.
+* For discussing with fellow users, please use Discord.
+* For security disclosures, please use Github's security advisory feature.
+* For collaborations and partnerships, please contact us at vllm-questions AT lists.berkeley.edu.
--- a/vllm-v0.6.2/vllm.egg-info/SOURCES.txt
+++ b/vllm-v0.6.2/vllm.egg-info/SOURCES.txt
@@ -0,0 +1,621 @@
+CMakeLists.txt
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+requirements-common.txt
+requirements-cpu.txt
+requirements-cuda.txt
+requirements-neuron.txt
+requirements-rocm.txt
+setup.py
+cmake/cpu_extension.cmake
+cmake/hipify.py
+cmake/utils.cmake
+ray_mlu/__init__.py
+ray_mlu/mlu.py
+ray_mlu/node.py
+ray_mlu/nsight.py
+ray_mlu/test_mlu.py
+tests/test_cache_block_hashing.py
+tests/test_config.py
+tests/test_embedded_commit.py
+tests/test_inputs.py
+tests/test_logger.py
+tests/test_logits_processor.py
+tests/test_regression.py
+tests/test_sampling_params.py
+tests/test_scalartype.py
+tests/test_sequence.py
+tests/test_sharded_state_loader.py
+tests/test_utils.py
+vllm/__init__.py
+vllm/_custom_ops.py
+vllm/_ipex_ops.py
+vllm/_mlu_ops.py
+vllm/beam_search.py
+vllm/block.py
+vllm/config.py
+vllm/connections.py
+vllm/envs.py
+vllm/forward_context.py
+vllm/logger.py
+vllm/logits_process.py
+vllm/outputs.py
+vllm/pooling_params.py
+vllm/py.typed
+vllm/sampling_params.py
+vllm/scalar_type.py
+vllm/scripts.py
+vllm/sequence.py
+vllm/tracing.py
+vllm/utils.py
+vllm/version.py
+vllm/version_config
+vllm.egg-info/PKG-INFO
+vllm.egg-info/SOURCES.txt
+vllm.egg-info/dependency_links.txt
+vllm.egg-info/entry_points.txt
+vllm.egg-info/requires.txt
+vllm.egg-info/top_level.txt
+vllm/adapter_commons/__init__.py
+vllm/adapter_commons/layers.py
+vllm/adapter_commons/models.py
+vllm/adapter_commons/request.py
+vllm/adapter_commons/utils.py
+vllm/adapter_commons/worker_manager.py
+vllm/assets/__init__.py
+vllm/assets/audio.py
+vllm/assets/base.py
+vllm/assets/image.py
+vllm/assets/video.py
+vllm/attention/__init__.py
+vllm/attention/layer.py
+vllm/attention/selector.py
+vllm/attention/backends/__init__.py
+vllm/attention/backends/abstract.py
+vllm/attention/backends/blocksparse_attn.py
+vllm/attention/backends/flash_attn.py
+vllm/attention/backends/flashinfer.py
+vllm/attention/backends/hpu_attn.py
+vllm/attention/backends/ipex_attn.py
+vllm/attention/backends/mlu_attn.py
+vllm/attention/backends/openvino.py
+vllm/attention/backends/pallas.py
+vllm/attention/backends/placeholder_attn.py
+vllm/attention/backends/rocm_flash_attn.py
+vllm/attention/backends/torch_sdpa.py
+vllm/attention/backends/utils.py
+vllm/attention/backends/xformers.py
+vllm/attention/ops/__init__.py
+vllm/attention/ops/hpu_paged_attn.py
+vllm/attention/ops/ipex_attn.py
+vllm/attention/ops/paged_attn.py
+vllm/attention/ops/prefix_prefill.py
+vllm/attention/ops/triton_flash_attention.py
+vllm/attention/ops/blocksparse_attention/__init__.py
+vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py
+vllm/attention/ops/blocksparse_attention/interface.py
+vllm/attention/ops/blocksparse_attention/utils.py
+vllm/compilation/__init__.py
+vllm/compilation/backends.py
+vllm/compilation/compile_context.py
+vllm/compilation/config.py
+vllm/compilation/counter.py
+vllm/compilation/decorators.py
+vllm/compilation/fusion.py
+vllm/compilation/inductor_pass.py
+vllm/compilation/levels.py
+vllm/compilation/reshapes.py
+vllm/compilation/wrapper.py
+vllm/core/__init__.py
+vllm/core/block_manager.py
+vllm/core/evictor.py
+vllm/core/interfaces.py
+vllm/core/placeholder_block_space_manager.py
+vllm/core/scheduler.py
+vllm/core/block/__init__.py
+vllm/core/block/block_table.py
+vllm/core/block/common.py
+vllm/core/block/cpu_gpu_block_allocator.py
+vllm/core/block/interfaces.py
+vllm/core/block/naive_block.py
+vllm/core/block/prefix_caching_block.py
+vllm/core/block/utils.py
+vllm/distributed/__init__.py
+vllm/distributed/communication_op.py
+vllm/distributed/parallel_state.py
+vllm/distributed/utils.py
+vllm/distributed/device_communicators/__init__.py
+vllm/distributed/device_communicators/cuda_wrapper.py
+vllm/distributed/device_communicators/custom_all_reduce.py
+vllm/distributed/device_communicators/custom_all_reduce_utils.py
+vllm/distributed/device_communicators/hpu_communicator.py
+vllm/distributed/device_communicators/pynccl.py
+vllm/distributed/device_communicators/pynccl_wrapper.py
+vllm/distributed/device_communicators/shm_broadcast.py
+vllm/distributed/device_communicators/tpu_communicator.py
+vllm/distributed/device_communicators/xpu_communicator.py
+vllm/engine/__init__.py
+vllm/engine/arg_utils.py
+vllm/engine/async_llm_engine.py
+vllm/engine/async_timeout.py
+vllm/engine/llm_engine.py
+vllm/engine/metrics.py
+vllm/engine/metrics_types.py
+vllm/engine/protocol.py
+vllm/engine/multiprocessing/__init__.py
+vllm/engine/multiprocessing/client.py
+vllm/engine/multiprocessing/engine.py
+vllm/engine/output_processor/__init__.py
+vllm/engine/output_processor/interfaces.py
+vllm/engine/output_processor/multi_step.py
+vllm/engine/output_processor/single_step.py
+vllm/engine/output_processor/stop_checker.py
+vllm/engine/output_processor/util.py
+vllm/entrypoints/__init__.py
+vllm/entrypoints/api_server.py
+vllm/entrypoints/chat_utils.py
+vllm/entrypoints/launcher.py
+vllm/entrypoints/llm.py
+vllm/entrypoints/logger.py
+vllm/entrypoints/openai/__init__.py
+vllm/entrypoints/openai/api_server.py
+vllm/entrypoints/openai/cli_args.py
+vllm/entrypoints/openai/logits_processors.py
+vllm/entrypoints/openai/protocol.py
+vllm/entrypoints/openai/run_batch.py
+vllm/entrypoints/openai/serving_chat.py
+vllm/entrypoints/openai/serving_completion.py
+vllm/entrypoints/openai/serving_embedding.py
+vllm/entrypoints/openai/serving_engine.py
+vllm/entrypoints/openai/serving_tokenization.py
+vllm/entrypoints/openai/tool_parsers/__init__.py
+vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py
+vllm/entrypoints/openai/tool_parsers/utils.py
+vllm/executor/__init__.py
+vllm/executor/cpu_executor.py
+vllm/executor/distributed_gpu_executor.py
+vllm/executor/distributed_mlu_executor.py
+vllm/executor/executor_base.py
+vllm/executor/gpu_executor.py
+vllm/executor/hpu_executor.py
+vllm/executor/mlu_executor.py
+vllm/executor/msgspec_utils.py
+vllm/executor/multiproc_gpu_executor.py
+vllm/executor/multiproc_mlu_executor.py
+vllm/executor/multiproc_worker_utils.py
+vllm/executor/multiproc_xpu_executor.py
+vllm/executor/neuron_executor.py
+vllm/executor/openvino_executor.py
+vllm/executor/ray_gpu_executor.py
+vllm/executor/ray_hpu_executor.py
+vllm/executor/ray_mlu_executor.py
+vllm/executor/ray_tpu_executor.py
+vllm/executor/ray_utils.py
+vllm/executor/ray_xpu_executor.py
+vllm/executor/tpu_executor.py
+vllm/executor/xpu_executor.py
+vllm/inputs/__init__.py
+vllm/inputs/data.py
+vllm/inputs/parse.py
+vllm/inputs/preprocess.py
+vllm/inputs/registry.py
+vllm/logging_utils/__init__.py
+vllm/logging_utils/formatter.py
+vllm/lora/__init__.py
+vllm/lora/fully_sharded_layers.py
+vllm/lora/layers.py
+vllm/lora/lora.py
+vllm/lora/models.py
+vllm/lora/punica.py
+vllm/lora/request.py
+vllm/lora/utils.py
+vllm/lora/worker_manager.py
+vllm/lora/ops/__init__.py
+vllm/lora/ops/bgmv_expand.py
+vllm/lora/ops/bgmv_expand_slice.py
+vllm/lora/ops/bgmv_shrink.py
+vllm/lora/ops/sgmv_expand.py
+vllm/lora/ops/sgmv_expand_slice.py
+vllm/lora/ops/sgmv_shrink.py
+vllm/lora/ops/utils.py
+vllm/model_executor/__init__.py
+vllm/model_executor/custom_op.py
+vllm/model_executor/parameter.py
+vllm/model_executor/pooling_metadata.py
+vllm/model_executor/sampling_metadata.py
+vllm/model_executor/utils.py
+vllm/model_executor/guided_decoding/__init__.py
+vllm/model_executor/guided_decoding/guided_fields.py
+vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py
+vllm/model_executor/guided_decoding/outlines_decoding.py
+vllm/model_executor/guided_decoding/outlines_logits_processors.py
+vllm/model_executor/layers/__init__.py
+vllm/model_executor/layers/activation.py
+vllm/model_executor/layers/layernorm.py
+vllm/model_executor/layers/linear.py
+vllm/model_executor/layers/logits_processor.py
+vllm/model_executor/layers/pooler.py
+vllm/model_executor/layers/rejection_sampler.py
+vllm/model_executor/layers/resampler.py
+vllm/model_executor/layers/rotary_embedding.py
+vllm/model_executor/layers/sampler.py
+vllm/model_executor/layers/spec_decode_base_sampler.py
+vllm/model_executor/layers/typical_acceptance_sampler.py
+vllm/model_executor/layers/vocab_parallel_embedding.py
+vllm/model_executor/layers/fused_moe/__init__.py
+vllm/model_executor/layers/fused_moe/fused_marlin_moe.py
+vllm/model_executor/layers/fused_moe/fused_moe.py
+vllm/model_executor/layers/fused_moe/layer.py
+vllm/model_executor/layers/fused_moe/moe_pallas.py
+vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
+vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json
+vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
+vllm/model_executor/layers/mamba/__init__.py
+vllm/model_executor/layers/mamba/mamba_mixer.py
+vllm/model_executor/layers/mamba/ops/__init__.py
+vllm/model_executor/layers/mamba/ops/causal_conv1d.py
+vllm/model_executor/layers/mamba/ops/mamba_ssm.py
+vllm/model_executor/layers/quantization/__init__.py
+vllm/model_executor/layers/quantization/aqlm.py
+vllm/model_executor/layers/quantization/awq.py
+vllm/model_executor/layers/quantization/awq_marlin.py
+vllm/model_executor/layers/quantization/awq_triton.py
+vllm/model_executor/layers/quantization/base_config.py
+vllm/model_executor/layers/quantization/bitsandbytes.py
+vllm/model_executor/layers/quantization/deepspeedfp.py
+vllm/model_executor/layers/quantization/experts_int8.py
+vllm/model_executor/layers/quantization/fbgemm_fp8.py
+vllm/model_executor/layers/quantization/fp8.py
+vllm/model_executor/layers/quantization/gguf.py
+vllm/model_executor/layers/quantization/gptq.py
+vllm/model_executor/layers/quantization/gptq_marlin.py
+vllm/model_executor/layers/quantization/gptq_marlin_24.py
+vllm/model_executor/layers/quantization/ipex_quant.py
+vllm/model_executor/layers/quantization/kv_cache.py
+vllm/model_executor/layers/quantization/marlin.py
+vllm/model_executor/layers/quantization/modelopt.py
+vllm/model_executor/layers/quantization/neuron_quant.py
+vllm/model_executor/layers/quantization/qqq.py
+vllm/model_executor/layers/quantization/schema.py
+vllm/model_executor/layers/quantization/tpu_int8.py
+vllm/model_executor/layers/quantization/compressed_tensors/__init__.py
+vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
+vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py
+vllm/model_executor/layers/quantization/compressed_tensors/utils.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
+vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py
+vllm/model_executor/layers/quantization/kernels/MPLinearKernel.py
+vllm/model_executor/layers/quantization/kernels/__init__.py
+vllm/model_executor/layers/quantization/kernels/exllama.py
+vllm/model_executor/layers/quantization/kernels/machete.py
+vllm/model_executor/layers/quantization/kernels/marlin.py
+vllm/model_executor/layers/quantization/utils/__init__.py
+vllm/model_executor/layers/quantization/utils/layer_utils.py
+vllm/model_executor/layers/quantization/utils/machete_utils.py
+vllm/model_executor/layers/quantization/utils/marlin_utils.py
+vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
+vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
+vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
+vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py
+vllm/model_executor/layers/quantization/utils/quant_utils.py
+vllm/model_executor/layers/quantization/utils/w8a8_utils.py
+vllm/model_executor/model_loader/__init__.py
+vllm/model_executor/model_loader/loader.py
+vllm/model_executor/model_loader/neuron.py
+vllm/model_executor/model_loader/openvino.py
+vllm/model_executor/model_loader/tensorizer.py
+vllm/model_executor/model_loader/utils.py
+vllm/model_executor/model_loader/weight_utils.py
+vllm/model_executor/models/__init__.py
+vllm/model_executor/models/arctic.py
+vllm/model_executor/models/baichuan.py
+vllm/model_executor/models/bart.py
+vllm/model_executor/models/bert.py
+vllm/model_executor/models/blip.py
+vllm/model_executor/models/blip2.py
+vllm/model_executor/models/bloom.py
+vllm/model_executor/models/chameleon.py
+vllm/model_executor/models/chatglm.py
+vllm/model_executor/models/clip.py
+vllm/model_executor/models/commandr.py
+vllm/model_executor/models/dbrx.py
+vllm/model_executor/models/decilm.py
+vllm/model_executor/models/deepseek.py
+vllm/model_executor/models/deepseek_v2.py
+vllm/model_executor/models/eagle.py
+vllm/model_executor/models/exaone.py
+vllm/model_executor/models/falcon.py
+vllm/model_executor/models/florence2.py
+vllm/model_executor/models/fuyu.py
+vllm/model_executor/models/gemma.py
+vllm/model_executor/models/gemma2.py
+vllm/model_executor/models/glm4_vision_encoder.py
+vllm/model_executor/models/gpt2.py
+vllm/model_executor/models/gpt_bigcode.py
+vllm/model_executor/models/gpt_j.py
+vllm/model_executor/models/gpt_neox.py
+vllm/model_executor/models/granite.py
+vllm/model_executor/models/granitemoe.py
+vllm/model_executor/models/h2ovl.py
+vllm/model_executor/models/hunyuan.py
+vllm/model_executor/models/idefics2_vision_model.py
+vllm/model_executor/models/idefics3.py
+vllm/model_executor/models/interfaces.py
+vllm/model_executor/models/interfaces_base.py
+vllm/model_executor/models/intern_vit.py
+vllm/model_executor/models/internlm2.py
+vllm/model_executor/models/internlm2_ve.py
+vllm/model_executor/models/internvl.py
+vllm/model_executor/models/jais.py
+vllm/model_executor/models/jamba.py
+vllm/model_executor/models/llama.py
+vllm/model_executor/models/llava.py
+vllm/model_executor/models/llava_next.py
+vllm/model_executor/models/llava_next_video.py
+vllm/model_executor/models/llava_onevision.py
+vllm/model_executor/models/mamba.py
+vllm/model_executor/models/mamba_cache.py
+vllm/model_executor/models/medusa.py
+vllm/model_executor/models/minicpm.py
+vllm/model_executor/models/minicpm3.py
+vllm/model_executor/models/minicpmv.py
+vllm/model_executor/models/mixtral.py
+vllm/model_executor/models/mixtral_quant.py
+vllm/model_executor/models/mllama.py
+vllm/model_executor/models/mlp_speculator.py
+vllm/model_executor/models/module_mapping.py
+vllm/model_executor/models/molmo.py
+vllm/model_executor/models/mpt.py
+vllm/model_executor/models/nemotron.py
+vllm/model_executor/models/nvlm_d.py
+vllm/model_executor/models/olmo.py
+vllm/model_executor/models/olmoe.py
+vllm/model_executor/models/opt.py
+vllm/model_executor/models/orion.py
+vllm/model_executor/models/paligemma.py
+vllm/model_executor/models/persimmon.py
+vllm/model_executor/models/phi.py
+vllm/model_executor/models/phi3.py
+vllm/model_executor/models/phi3_small.py
+vllm/model_executor/models/phi3v.py
+vllm/model_executor/models/phimoe.py
+vllm/model_executor/models/pixtral.py
+vllm/model_executor/models/qwen.py
+vllm/model_executor/models/qwen2.py
+vllm/model_executor/models/qwen2_audio.py
+vllm/model_executor/models/qwen2_cls.py
+vllm/model_executor/models/qwen2_moe.py
+vllm/model_executor/models/qwen2_rm.py
+vllm/model_executor/models/qwen2_vl.py
+vllm/model_executor/models/registry.py
+vllm/model_executor/models/roberta.py
+vllm/model_executor/models/siglip.py
+vllm/model_executor/models/solar.py
+vllm/model_executor/models/stablelm.py
+vllm/model_executor/models/starcoder2.py
+vllm/model_executor/models/ultravox.py
+vllm/model_executor/models/utils.py
+vllm/model_executor/models/xverse.py
+vllm/multimodal/__init__.py
+vllm/multimodal/audio.py
+vllm/multimodal/base.py
+vllm/multimodal/image.py
+vllm/multimodal/inputs.py
+vllm/multimodal/processing.py
+vllm/multimodal/registry.py
+vllm/multimodal/utils.py
+vllm/multimodal/video.py
+vllm/platforms/__init__.py
+vllm/platforms/cpu.py
+vllm/platforms/cuda.py
+vllm/platforms/hpu.py
+vllm/platforms/interface.py
+vllm/platforms/mlu.py
+vllm/platforms/neuron.py
+vllm/platforms/openvino.py
+vllm/platforms/rocm.py
+vllm/platforms/tpu.py
+vllm/platforms/xpu.py
+vllm/plugins/__init__.py
+vllm/profiler/__init__.py
+vllm/profiler/layerwise_profile.py
+vllm/profiler/utils.py
+vllm/prompt_adapter/__init__.py
+vllm/prompt_adapter/layers.py
+vllm/prompt_adapter/models.py
+vllm/prompt_adapter/request.py
+vllm/prompt_adapter/utils.py
+vllm/prompt_adapter/worker_manager.py
+vllm/spec_decode/__init__.py
+vllm/spec_decode/batch_expansion.py
+vllm/spec_decode/draft_model_runner.py
+vllm/spec_decode/interfaces.py
+vllm/spec_decode/medusa_worker.py
+vllm/spec_decode/metrics.py
+vllm/spec_decode/mlp_speculator_worker.py
+vllm/spec_decode/mlu_batch_expansion.py
+vllm/spec_decode/mlu_draft_model_runner.py
+vllm/spec_decode/mlu_medusa_worker.py
+vllm/spec_decode/mlu_metrics.py
+vllm/spec_decode/mlu_mlp_speculator_worker.py
+vllm/spec_decode/mlu_multi_step_worker.py
+vllm/spec_decode/mlu_ngram_worker.py
+vllm/spec_decode/mlu_smaller_tp_proposer_worker.py
+vllm/spec_decode/mlu_spec_decode_worker.py
+vllm/spec_decode/mlu_target_model_runner.py
+vllm/spec_decode/mqa_scorer.py
+vllm/spec_decode/multi_step_worker.py
+vllm/spec_decode/ngram_worker.py
+vllm/spec_decode/proposer_worker_base.py
+vllm/spec_decode/smaller_tp_proposer_worker.py
+vllm/spec_decode/spec_decode_worker.py
+vllm/spec_decode/target_model_runner.py
+vllm/spec_decode/top1_proposer.py
+vllm/spec_decode/util.py
+vllm/transformers_utils/__init__.py
+vllm/transformers_utils/config.py
+vllm/transformers_utils/detokenizer.py
+vllm/transformers_utils/detokenizer_utils.py
+vllm/transformers_utils/processor.py
+vllm/transformers_utils/tokenizer.py
+vllm/transformers_utils/utils.py
+vllm/transformers_utils/configs/__init__.py
+vllm/transformers_utils/configs/arctic.py
+vllm/transformers_utils/configs/chatglm.py
+vllm/transformers_utils/configs/dbrx.py
+vllm/transformers_utils/configs/eagle.py
+vllm/transformers_utils/configs/exaone.py
+vllm/transformers_utils/configs/falcon.py
+vllm/transformers_utils/configs/h2ovl.py
+vllm/transformers_utils/configs/internvl.py
+vllm/transformers_utils/configs/jais.py
+vllm/transformers_utils/configs/medusa.py
+vllm/transformers_utils/configs/mllama.py
+vllm/transformers_utils/configs/mlp_speculator.py
+vllm/transformers_utils/configs/mpt.py
+vllm/transformers_utils/configs/nemotron.py
+vllm/transformers_utils/configs/nvlm_d.py
+vllm/transformers_utils/configs/solar.py
+vllm/transformers_utils/configs/ultravox.py
+vllm/transformers_utils/tokenizer_group/__init__.py
+vllm/transformers_utils/tokenizer_group/base_tokenizer_group.py
+vllm/transformers_utils/tokenizer_group/ray_tokenizer_group.py
+vllm/transformers_utils/tokenizer_group/tokenizer_group.py
+vllm/transformers_utils/tokenizers/__init__.py
+vllm/transformers_utils/tokenizers/mistral.py
+vllm/triton_utils/__init__.py
+vllm/triton_utils/custom_cache_manager.py
+vllm/triton_utils/importing.py
+vllm/usage/__init__.py
+vllm/usage/usage_lib.py
+vllm/v1/__init__.py
+vllm/v1/outputs.py
+vllm/v1/request.py
+vllm/v1/serial_utils.py
+vllm/v1/utils.py
+vllm/v1/attention/__init__.py
+vllm/v1/attention/backends/__init__.py
+vllm/v1/attention/backends/flash_attn.py
+vllm/v1/core/__init__.py
+vllm/v1/core/encoder_cache_manager.py
+vllm/v1/core/kv_cache_manager.py
+vllm/v1/core/kv_cache_utils.py
+vllm/v1/core/scheduler.py
+vllm/v1/engine/__init__.py
+vllm/v1/engine/async_llm.py
+vllm/v1/engine/async_stream.py
+vllm/v1/engine/core.py
+vllm/v1/engine/core_client.py
+vllm/v1/engine/detokenizer.py
+vllm/v1/engine/llm_engine.py
+vllm/v1/engine/mm_input_mapper.py
+vllm/v1/engine/processor.py
+vllm/v1/executor/__init__.py
+vllm/v1/executor/gpu_executor.py
+vllm/v1/sample/__init__.py
+vllm/v1/sample/metadata.py
+vllm/v1/sample/sampler.py
+vllm/v1/worker/__init__.py
+vllm/v1/worker/gpu_model_runner.py
+vllm/v1/worker/gpu_worker.py
+vllm/worker/__init__.py
+vllm/worker/cache_engine.py
+vllm/worker/cpu_embedding_model_runner.py
+vllm/worker/cpu_enc_dec_model_runner.py
+vllm/worker/cpu_model_runner.py
+vllm/worker/cpu_worker.py
+vllm/worker/embedding_model_runner.py
+vllm/worker/enc_dec_model_runner.py
+vllm/worker/hpu_model_runner.py
+vllm/worker/hpu_worker.py
+vllm/worker/mlu_enc_dec_model_runner.py
+vllm/worker/mlu_model_runner.py
+vllm/worker/mlu_multi_step_model_runner.py
+vllm/worker/mlu_multi_step_worker.py
+vllm/worker/mlu_worker.py
+vllm/worker/model_runner.py
+vllm/worker/model_runner_base.py
+vllm/worker/multi_step_model_runner.py
+vllm/worker/multi_step_tpu_worker.py
+vllm/worker/multi_step_worker.py
+vllm/worker/neuron_model_runner.py
+vllm/worker/neuron_worker.py
+vllm/worker/openvino_model_runner.py
+vllm/worker/openvino_worker.py
+vllm/worker/tpu_model_runner.py
+vllm/worker/tpu_worker.py
+vllm/worker/utils.py
+vllm/worker/worker.py
+vllm/worker/worker_base.py
+vllm/worker/xpu_model_runner.py
+vllm/worker/xpu_worker.py
--- a/vllm-v0.6.2/vllm.egg-info/dependency_links.txt
+++ b/vllm-v0.6.2/vllm.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
--- a/vllm-v0.6.2/vllm.egg-info/entry_points.txt
+++ b/vllm-v0.6.2/vllm.egg-info/entry_points.txt
@@ -0,0 +1,2 @@
+[console_scripts]
+vllm = vllm.scripts:main
--- a/vllm-v0.6.2/vllm.egg-info/requires.txt
+++ b/vllm-v0.6.2/vllm.egg-info/requires.txt
@@ -0,0 +1,63 @@
+psutil
+sentencepiece
+numpy<2.0.0
+requests>=2.26.0
+tqdm
+py-cpuinfo
+transformers>=4.45.2
+tokenizers>=0.19.1
+protobuf
+aiohttp
+openai>=1.45.0
+uvicorn[standard]
+pydantic>=2.9
+pillow
+prometheus_client>=0.18.0
+prometheus-fastapi-instrumentator>=7.0.0
+tiktoken>=0.6.0
+lm-format-enforcer<0.11,>=0.10.9
+outlines<0.1,>=0.0.43
+typing_extensions>=4.10
+filelock>=3.10.4
+partial-json-parser
+pyzmq
+msgspec
+gguf==0.10.0
+importlib_metadata
+mistral_common[opencv]>=1.5.0
+pyyaml
+einops
+compressed-tensors==0.8.0
+tensorizer
+matplotlib>=3.7.4
+accelerate
+loguru
+ray==2.40.0
+triton==3.0.0
+torch==2.5.0
+torch-mlu>=1.23.1
+torch_mlu_ops>=1.2.2
+xformers==0.0.24
+datasets
+transformers_stream_generator
+huggingface-hub==0.25.2
+
+[:python_version < "3.9"]
+fastapi<0.113.0,>=0.107.0
+
+[:python_version > "3.11"]
+six>=1.16.0
+setuptools>=74.1.1
+
+[:python_version >= "3.9"]
+fastapi!=0.113.*,!=0.114.0,>=0.107.0
+
+[audio]
+librosa
+soundfile
+
+[tensorizer]
+tensorizer>=2.9.0
+
+[video]
+decord
--- a/vllm-v0.6.2/vllm.egg-info/top_level.txt
+++ b/vllm-v0.6.2/vllm.egg-info/top_level.txt
@@ -0,0 +1,2 @@
+ray_mlu
+vllm