6a512a00df
Co-authored-by: Roger Wang <ywang@roblox.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
28 lines
1.1 KiB
Docker
28 lines
1.1 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
|
|
|
|
# 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
|
|
|
|
# These packages will be in rocketce eventually
|
|
RUN pip install -v cmake xformers torch==2.3.1 uvloop==0.20.0 -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing
|
|
|
|
RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install
|
|
|
|
WORKDIR /workspace/
|
|
|
|
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
|
|
|
|
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
|