vllm/Dockerfile.ppc64le

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

# 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"]