mirror of https://github.com/vllm-project/vllm
39 lines
1.6 KiB
Docker
39 lines
1.6 KiB
Docker
FROM mambaorg/micromamba
|
|
ARG MAMBA_DOCKERFILE_ACTIVATE=1
|
|
USER root
|
|
|
|
ENV PATH="/usr/local/cargo/bin:$PATH:/opt/conda/bin/"
|
|
|
|
RUN apt-get update -y && apt-get install -y git wget curl vim libnuma-dev libsndfile-dev libprotobuf-dev build-essential ffmpeg libsm6 libxext6 libgl1 libssl-dev
|
|
|
|
# Some packages in requirements-cpu are installed here
|
|
# IBM provides optimized packages for ppc64le processors in the open-ce project for mamba
|
|
# Currently these may not be available for venv or pip directly
|
|
RUN micromamba install -y -n base -c https://ftp.osuosl.org/pub/open-ce/1.11.0-p10/ -c defaults python=3.10 torchvision-cpu=0.16.2 rust && micromamba clean --all --yes
|
|
|
|
COPY ./ /workspace/vllm
|
|
|
|
WORKDIR /workspace/vllm
|
|
ARG GIT_REPO_CHECK=0
|
|
RUN --mount=type=bind,source=.git,target=.git \
|
|
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh; fi
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
RUSTFLAGS='-L /opt/conda/lib' pip install -v --prefer-binary --extra-index-url https://repo.fury.io/mgiessing \
|
|
'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
|
|
torch==2.3.1 \
|
|
-r requirements-cpu.txt \
|
|
xformers uvloop==0.20.0
|
|
|
|
RUN --mount=type=bind,source=.git,target=.git \
|
|
VLLM_TARGET_DEVICE=cpu python3 setup.py install
|
|
|
|
# install development dependencies (for testing)
|
|
RUN python3 -m pip install -e tests/vllm_test_utils
|
|
|
|
WORKDIR /workspace/
|
|
|
|
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
|
|
|
|
ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]
|