vLLM 最新版 + CUDA 12.4

1# syntax=docker/dockerfile:1
2# ^ Required for BuildKit cache mounts and advanced features
3 
4# Generated by DockerFit (https://tools.eastondev.com/docker)
5# VLLM latest + CUDA 12.4 | Python 3.11
6# Multi-stage build for optimized image size
7 
8# ==============================================================================
9# Stage 1: Builder - Install dependencies and compile
10# ==============================================================================
11FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 AS builder
12 
13# Build arguments
14ARG DEBIAN_FRONTEND=noninteractive
15 
16# Environment variables
17ENV PYTHONUNBUFFERED=1
18ENV PYTHONDONTWRITEBYTECODE=1
19ENV TORCH_CUDA_ARCH_LIST="8.0;8.6;8.9;9.0"
20 
21# Install Python 3.11 from deadsnakes PPA (Ubuntu 22.04)
22RUN apt-get update && apt-get install -y --no-install-recommends \
23    software-properties-common \
24    && add-apt-repository -y ppa:deadsnakes/ppa \
25    && apt-get update && apt-get install -y --no-install-recommends \
26    python3.11 \
27    python3.11-venv \
28    python3.11-dev \
29    build-essential \
30    git \
31    ninja-build
32    && rm -rf /var/lib/apt/lists/*
33 
34# Create virtual environment
35ENV VIRTUAL_ENV=/opt/venv
36RUN python3.11 -m venv $VIRTUAL_ENV
37ENV PATH="$VIRTUAL_ENV/bin:$PATH"
38 
39# Upgrade pip
40RUN pip install --no-cache-dir --upgrade pip setuptools wheel
41 
42# Install vLLM with BuildKit cache
43# Pre-install packaging for potential source builds
44RUN --mount=type=cache,target=/root/.cache/pip \
45    pip install packaging && \
46    pip install vllm
47 
48# Install project dependencies
49COPY requirements.txt .
50RUN --mount=type=cache,target=/root/.cache/pip \
51    pip install -r requirements.txt
52 
53# ==============================================================================
54# Stage 2: Runtime - Minimal production image
55# ==============================================================================
56FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04 AS runtime
57 
58# Labels
59LABEL maintainer="Generated by DockerFit"
60LABEL version="latest"
61LABEL description="VLLM latest + CUDA 12.4"
62 
63# Environment variables
64ENV PYTHONUNBUFFERED=1
65ENV PYTHONDONTWRITEBYTECODE=1
66ENV NVIDIA_VISIBLE_DEVICES=all
67ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
68 
69# Install Python 3.11 runtime from deadsnakes PPA (Ubuntu 22.04)
70RUN apt-get update && apt-get install -y --no-install-recommends \
71    software-properties-common \
72    && add-apt-repository -y ppa:deadsnakes/ppa \
73    && apt-get update && apt-get install -y --no-install-recommends \
74    python3.11 \
75    libgomp1 \
76    ninja-build
77    && apt-get remove -y software-properties-common \
78    && apt-get autoremove -y \
79    && rm -rf /var/lib/apt/lists/*
80 
81# Create non-root user for security
82ARG USERNAME=appuser
83ARG USER_UID=1000
84ARG USER_GID=$USER_UID
85RUN groupadd --gid $USER_GID $USERNAME \
86    && useradd --uid $USER_UID --gid $USER_GID -m $USERNAME
87 
88# Copy virtual environment from builder
89COPY --from=builder --chown=$USERNAME:$USERNAME /opt/venv /opt/venv
90ENV VIRTUAL_ENV=/opt/venv
91ENV PATH="$VIRTUAL_ENV/bin:$PATH"
92 
93# Set working directory
94WORKDIR /app
95 
96# Copy application code
97COPY --chown=$USERNAME:$USERNAME . .
98 
99# Switch to non-root user
100USER $USERNAME
101 
102# Expose port
103EXPOSE 8000
104 
105# Default command
106CMD ["python", "main.py"]