luojunhui 1 day ago
parent
commit
c5e3e8e245
3 changed files with 163 additions and 9 deletions
  1. 2 6
      Dockerfile
  2. 1 1
      docker-compose.yaml
  3. 160 2
      requirements.txt

+ 2 - 6
Dockerfile

@@ -11,14 +11,10 @@ RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone \
 
 COPY requirements.txt .
 RUN pip install --no-cache-dir --upgrade pillow
+RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
 EXPOSE 8000
 
-CMD ["python3", "-m", "vllm.entrypoints.openai.api_server",
-     "--model", "/app/model/Qwen3-Embedding-4B",
-     "--dtype", "float16",
-     "--host", "0.0.0.0",
-     "--port", "8000",
-     "--trust-remote-code"]
+CMD ["python3", "-m", "vllm.entrypoints.openai.api_server", "--model", "/app/model/Qwen3-Embedding-4B", "--dtype", "float16", "--host", "0.0.0.0", "--port", "8000"]

+ 1 - 1
docker-compose.yaml

@@ -8,7 +8,7 @@ services:
       - "8000:8000"
     volumes:
       - .:/app
-      - ./models:/app/model   # 挂载模型
+      - ./models/Qwen3-Embedding-4B:/app/model/Qwen3-Embedding-4B  # 挂载模型
     environment:
       - PYTHONUNBUFFERED=1
     deploy:

+ 160 - 2
requirements.txt

@@ -1,2 +1,160 @@
-quart
-quart-cors
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.15
+aiosignal==1.4.0
+annotated-types==0.7.0
+anyio==4.10.0
+astor==0.8.1
+attrs==25.3.0
+blake3==1.0.5
+blinker==1.9.0
+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==0.10.2
+cupy-cuda12x==13.6.0
+depyf==0.19.0
+dill==0.4.0
+diskcache==5.6.3
+distro==1.9.0
+dnspython==2.8.0
+einops==0.8.1
+email-validator==2.3.0
+fastapi==0.116.1
+fastapi-cli==0.0.10
+fastapi-cloud-cli==0.1.5
+fastrlock==0.8.3
+filelock==3.19.1
+Flask==3.1.2
+frozenlist==1.7.0
+fsspec==2025.9.0
+gguf==0.17.1
+grpcio==1.74.0
+h11==0.16.0
+h2==4.3.0
+hf-xet==1.1.9
+hpack==4.1.0
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.34.4
+Hypercorn==0.17.3
+hyperframe==6.1.0
+idna==3.10
+interegular==0.3.3
+itsdangerous==2.2.0
+Jinja2==3.1.6
+jiter==0.10.0
+jsonschema==4.25.1
+jsonschema-specifications==2025.9.1
+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==3.0.2
+mdurl==0.1.2
+milvus-lite==2.5.1
+mistral_common==1.8.4
+mpmath==1.3.0
+msgpack==1.1.1
+msgspec==0.19.0
+multidict==6.6.4
+networkx==3.5
+ninja==1.13.0
+numba==0.61.2
+numpy==2.2.6
+nvidia-cublas-cu12==12.6.4.1
+nvidia-cuda-cupti-cu12==12.6.80
+nvidia-cuda-nvrtc-cu12==12.6.77
+nvidia-cuda-runtime-cu12==12.6.77
+nvidia-cudnn-cu12==9.5.1.17
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cufile-cu12==1.11.1.6
+nvidia-curand-cu12==10.3.7.77
+nvidia-cusolver-cu12==11.7.1.2
+nvidia-cusparse-cu12==12.5.4.2
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+openai==1.106.1
+openai-harmony==0.0.4
+opencv-python-headless==4.12.0.88
+outlines_core==0.2.10
+packaging==25.0
+pandas==2.3.2
+partial-json-parser==0.2.1.1.post6
+pillow==11.3.0
+priority==2.0.0
+prometheus-fastapi-instrumentator==7.1.0
+prometheus_client==0.22.1
+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-extra-types==2.10.5
+pydantic_core==2.33.2
+Pygments==2.19.2
+pymilvus==2.6.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-json-logger==3.3.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.0.2
+Quart==0.20.0
+quart-cors==0.8.0
+ray==2.49.1
+referencing==0.36.2
+regex==2025.9.1
+requests==2.32.5
+rich==14.1.0
+rich-toolkit==0.15.1
+rignore==0.6.4
+rpds-py==0.27.1
+safetensors==0.6.2
+scipy==1.16.1
+sentencepiece==0.2.1
+sentry-sdk==2.37.0
+setproctitle==1.3.7
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soundfile==0.13.1
+soxr==1.0.0
+starlette==0.47.3
+sympy==1.14.0
+tiktoken==0.11.0
+tokenizers==0.22.0
+torch==2.7.1
+torchaudio==2.7.1
+torchvision==0.22.1
+tqdm==4.67.1
+transformers==4.56.1
+triton==3.3.1
+typer==0.17.4
+typing-inspection==0.4.1
+typing_extensions==4.15.0
+tzdata==2025.2
+ujson==5.11.0
+urllib3==2.5.0
+uvicorn==0.35.0
+uvloop==0.21.0
+vllm==0.10.1.1
+watchfiles==1.1.0
+websockets==15.0.1
+Werkzeug==3.1.3
+wsproto==1.2.0
+xformers==0.0.31
+xgrammar==0.1.21
+yarl==1.20.1