vllm安装方法

1、安装vllm

• 参照文档
  https://docs.vllm.ai/en/latest/getting_started/quickstart.html

步骤

1)安装uv

curl -LsSf https://astral.sh/uv/install.sh | sh

2)创建环境

conda create -n myenv python=3.12 -y
conda activate myenv
pip install --upgrade uv
pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu118
uv pip install vllm --torch-backend=cu11.8 
# 注意事项:重点要安装上torch==2.7.1,其中要求系统为20.04以上,18.04安装不了torch==2.7.1

2、验证vllm是否安装成功

如出现以下提示，则说明vllm调用成功

(vllm) root@dev-00805f96-686a-4adb-bdb0-c9abdf981f55-lfvwr:~/userdata/vllm-main# CUDA_VISIBLE_DEVICES=0 vllm serve /home/apulis-dev/userdata/vllm-main/checkpoint/checkpoint-630/checkpoint-630     --limit-mm-per-prompt '{"image":1}'     --gpu-memory-utilization 0.4     --api-key apulis123     --served-model-name OCR_MODEL     --tensor-parallel-size 1     --max-num-seqs 64     --max-model-len 512     --dtype auto     --disable-mm-preprocessor-cache     --seed 42     --host 127.0.0.1 --port 8004
INFO:     Started server process [69908]
INFO:     Waiting for application startup.
INFO:     Application startup complete

3、调用vllm

CUDA_VISIBLE_DEVICES=0 \
vllm serve /home/apulis-dev/userdata/vllm-main/checkpoint/checkpoint-630/checkpoint-630 \
    --limit-mm-per-prompt '{"image":1}' \
    --gpu-memory-utilization 0.4 \
    --api-key apulis123 \
    --served-model-name OCR_MODEL \
    --tensor-parallel-size 1 \
    --max-num-seqs 64 \
    --max-model-len 512 \
    --dtype auto \
    --disable-mm-preprocessor-cache \
    --seed 42 \
    --host 127.0.0.1 --port 8004

ssh -L 8004:localhost:8004 -p 45112 apulis-dev@gpu02.apulis.com.cn

4、代码版本及环境

代码版本:v0.10.2.rc1
环境:

name: vllm
channels:
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
  - https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge
dependencies:
  - _libgcc_mutex=0.1=main
  - _openmp_mutex=5.1=1_gnu
  - bzip2=1.0.8=h5eee18b_6
  - ca-certificates=2025.8.3=hbd8a1cb_0
  - expat=2.7.1=h6a678d5_0
  - ld_impl_linux-64=2.44=h1423503_1
  - libffi=3.4.6=h2dba641_1
  - libgcc=15.1.0=h767d61c_4
  - libgcc-ng=15.1.0=h69a702a_4
  - libgomp=15.1.0=h767d61c_4
  - liblzma=5.8.1=hb9d3cd8_2
  - liblzma-devel=5.8.1=hb9d3cd8_2
  - libstdcxx=15.1.0=h8f9b012_4
  - libstdcxx-ng=15.1.0=h4852527_4
  - libuuid=1.41.5=h5eee18b_0
  - libxcb=1.17.0=h9b100fa_0
  - ncurses=6.5=h7934f7d_0
  - openssl=3.5.2=h26f9b46_0
  - pip=25.2=pyh8b19718_0
  - pthread-stubs=0.4=hb9d3cd8_1002
  - python=3.12.11=h22baa00_0
  - readline=8.3=hc2a1206_0
  - sqlite=3.50.2=hb25bd0a_1
  - tk=8.6.15=h54e0aa7_0
  - tzdata=2025b=h04d1e81_0
  - wheel=0.45.1=py312h06a4308_0
  - xorg-libx11=1.8.12=h9b100fa_1
  - xorg-libxau=1.0.12=h9b100fa_0
  - xorg-libxdmcp=1.1.5=h9b100fa_0
  - xorg-xorgproto=2024.1=h5eee18b_1
  - xz=5.8.1=hbcc6ac9_2
  - xz-gpl-tools=5.8.1=hbcc6ac9_2
  - xz-tools=5.8.1=hb9d3cd8_2
  - zlib=1.2.13=h5eee18b_1
  - pip:
      - aiohappyeyeballs==2.6.1
      - aiohttp==3.12.15
      - aiosignal==1.4.0
      - airportsdata==20250811
      - annotated-types==0.7.0
      - anyio==4.10.0
      - astor==0.8.1
      - attrs==25.3.0
      - blake3==1.0.5
      - cachetools==6.2.0
      - cbor2==5.7.0
      - certifi==2025.8.3
      - cffi==1.17.1
      - charset-normalizer==3.4.3
      - click==8.2.1
      - cloudpickle==3.1.1
      - compressed-tensors==0.10.1
      - cupy-cuda12x==13.6.0
      - depyf==0.18.0
      - dill==0.4.0
      - diskcache==5.6.3
      - distro==1.9.0
      - dnspython==2.7.0
      - docopt==0.6.2
      - einops==0.8.1
      - email-validator==2.3.0
      - fastapi==0.116.1
      - fastapi-cli==0.0.8
      - fastapi-cloud-cli==0.1.5
      - fastrlock==0.8.3
      - filelock==3.19.1
      - frozenlist==1.7.0
      - fsspec==2024.6.1
      - gguf==0.17.1
      - googleapis-common-protos==1.70.0
      - grpcio==1.74.0
      - h11==0.16.0
      - hf-xet==1.1.8
      - httpcore==1.0.9
      - httptools==0.6.4
      - httpx==0.28.1
      - huggingface-hub==0.34.4
      - idna==3.10
      - importlib-metadata==8.7.0
      - interegular==0.3.3
      - jinja2==3.1.6
      - jiter==0.10.0
      - jsonschema==4.25.1
      - jsonschema-specifications==2025.4.1
      - lark==1.2.2
      - llguidance==0.7.30
      - llvmlite==0.44.0
      - lm-format-enforcer==0.10.12
      - markdown-it-py==4.0.0
      - markupsafe==2.1.5
      - mdurl==0.1.2
      - mistral-common==1.8.4
      - mpmath==1.3.0
      - msgpack==1.1.1
      - msgspec==0.19.0
      - multidict==6.6.4
      - nest-asyncio==1.6.0
      - networkx==3.3
      - ninja==1.13.0
      - num2words==0.5.14
      - numba==0.61.2
      - numpy==2.1.2
      - nvidia-cublas-cu11==11.11.3.6
      - nvidia-cublas-cu12==12.6.4.1
      - nvidia-cuda-cupti-cu11==11.8.87
      - nvidia-cuda-cupti-cu12==12.6.80
      - nvidia-cuda-nvrtc-cu11==11.8.89
      - nvidia-cuda-nvrtc-cu12==12.6.77
      - nvidia-cuda-runtime-cu11==11.8.89
      - nvidia-cuda-runtime-cu12==12.6.77
      - nvidia-cudnn-cu11==9.1.0.70
      - nvidia-cudnn-cu12==9.5.1.17
      - nvidia-cufft-cu11==10.9.0.58
      - nvidia-cufft-cu12==11.3.0.4
      - nvidia-cufile-cu12==1.11.1.6
      - nvidia-curand-cu11==10.3.0.86
      - nvidia-curand-cu12==10.3.7.77
      - nvidia-cusolver-cu11==11.4.1.48
      - nvidia-cusolver-cu12==11.7.1.2
      - nvidia-cusparse-cu11==11.7.5.86
      - nvidia-cusparse-cu12==12.5.4.2
      - nvidia-cusparselt-cu12==0.6.3
      - nvidia-nccl-cu11==2.21.5
      - nvidia-nccl-cu12==2.26.2
      - nvidia-nvjitlink-cu12==12.6.85
      - nvidia-nvtx-cu11==11.8.86
      - nvidia-nvtx-cu12==12.6.77
      - openai==1.102.0
      - openai-harmony==0.0.4
      - opencv-python-headless==4.12.0.88
      - opentelemetry-api==1.36.0
      - opentelemetry-exporter-otlp==1.36.0
      - opentelemetry-exporter-otlp-proto-common==1.36.0
      - opentelemetry-exporter-otlp-proto-grpc==1.36.0
      - opentelemetry-exporter-otlp-proto-http==1.36.0
      - opentelemetry-proto==1.36.0
      - opentelemetry-sdk==1.36.0
      - opentelemetry-semantic-conventions==0.57b0
      - opentelemetry-semantic-conventions-ai==0.4.13
      - outlines==0.1.11
      - outlines-core==0.1.26
      - packaging==25.0
      - partial-json-parser==0.2.1.1.post6
      - pillow==11.0.0
      - prometheus-client==0.22.1
      - prometheus-fastapi-instrumentator==7.1.0
      - propcache==0.3.2
      - protobuf==6.32.0
      - psutil==7.0.0
      - py-cpuinfo==9.0.0
      - pybase64==1.4.2
      - pycountry==24.6.1
      - pycparser==2.22
      - pydantic==2.11.7
      - pydantic-core==2.33.2
      - pydantic-extra-types==2.10.5
      - pygments==2.19.2
      - python-dotenv==1.1.1
      - python-json-logger==3.3.0
      - python-multipart==0.0.20
      - pyyaml==6.0.2
      - pyzmq==27.0.2
      - ray==2.49.0
      - referencing==0.36.2
      - regex==2025.7.34
      - requests==2.32.5
      - rich==14.1.0
      - rich-toolkit==0.15.0
      - rignore==0.6.4
      - rpds-py==0.27.0
      - safetensors==0.6.2
      - scipy==1.16.1
      - sentencepiece==0.2.1
      - sentry-sdk==2.35.1
      - setproctitle==1.3.6
      - setuptools==79.0.1
      - shellingham==1.5.4
      - six==1.17.0
      - sniffio==1.3.1
      - soundfile==0.13.1
      - soxr==0.5.0.post1
      - starlette==0.47.3
      - sympy==1.13.3
      - tiktoken==0.11.0
      - tokenizers==0.21.4
      - torch==2.7.0
      - torchaudio==2.7.0
      - torchvision==0.22.0
      - tqdm==