vllm/docker/Dockerfile.cpu at main · InflectionAI/vllm · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
# This vLLM Dockerfile is used to construct image that can build and run vLLM on x86 CPU platform.
#
# Build targets:
#   vllm-openai (default): used for serving deployment
#   vllm-test: used for CI tests
#   vllm-dev: used for development
#
# Build arguments:
#   PYTHON_VERSION=3.12 (default)|3.11|3.10|3.9
#   VLLM_CPU_DISABLE_AVX512=false (default)|true
#

######################### BASE IMAGE #########################
FROM ubuntu:22.04 AS base

WORKDIR /workspace/

ARG PYTHON_VERSION=3.12
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"

ENV LD_PRELOAD=""

# Install minimal dependencies and uv
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get update -y \
    && apt-get install -y --no-install-recommends ccache git curl wget ca-certificates \
        gcc-12 g++-12 libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 \
    && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12 \
    && curl -LsSf https://astral.sh/uv/install.sh | sh

ENV CCACHE_DIR=/root/.cache/ccache
ENV CMAKE_CXX_COMPILER_LAUNCHER=ccache

ENV PATH="/root/.local/bin:$PATH"
ENV VIRTUAL_ENV="/opt/venv"
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

ENV UV_HTTP_TIMEOUT=500

# Install Python dependencies
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
ENV UV_INDEX_STRATEGY="unsafe-best-match"
ENV UV_LINK_MODE="copy"
RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,src=requirements/common.txt,target=requirements/common.txt \
    --mount=type=bind,src=requirements/cpu.txt,target=requirements/cpu.txt \
    uv pip install --upgrade pip && \
    uv pip install -r requirements/cpu.txt

ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so:$LD_PRELOAD"

RUN echo 'ulimit -c 0' >> ~/.bashrc

######################### BUILD IMAGE #########################
FROM base AS vllm-build

ARG GIT_REPO_CHECK=0
# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
ARG VLLM_CPU_DISABLE_AVX512
ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}

WORKDIR /workspace/vllm

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,src=requirements/build.txt,target=requirements/build.txt \
    uv pip install -r requirements/build.txt

COPY . .
RUN --mount=type=bind,source=.git,target=.git \
    if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=cache,target=/workspace/vllm/.deps,sharing=locked \
    --mount=type=bind,source=.git,target=.git \
    VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel

######################### DEV IMAGE #########################
FROM vllm-build AS vllm-dev

WORKDIR /workspace/vllm

RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get install -y --no-install-recommends vim numactl xz-utils

# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -e tests/vllm_test_utils

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=bind,source=.git,target=.git \
    VLLM_TARGET_DEVICE=cpu python3 setup.py develop

RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -r requirements/dev.txt && \
    pre-commit install --hook-type pre-commit --hook-type commit-msg

ENTRYPOINT ["bash"]

######################### TEST IMAGE #########################
FROM base AS vllm-test

WORKDIR /workspace/

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
    cp requirements/test.in requirements/test-cpu.in && \
    sed -i '/mamba_ssm/d' requirements/test-cpu.in && \
    uv pip compile requirements/test-cpu.in -o requirements/cpu-test.txt && \
    uv pip install -r requirements/cpu-test.txt

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
    uv pip install dist/*.whl

ADD ./tests/ ./tests/
ADD ./examples/ ./examples/
ADD ./benchmarks/ ./benchmarks/
ADD ./vllm/collect_env.py .

# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -e tests/vllm_test_utils

ENTRYPOINT ["bash"]

######################### RELEASE IMAGE #########################
FROM base AS vllm-openai

WORKDIR /workspace/

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
    uv pip install dist/*.whl

ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]