FROM mambaorg/micromamba
ARG MAMBA_DOCKERFILE_ACTIVATE=1
USER root

RUN apt-get update  -y     && apt-get install -y git wget vim numactl gcc-12 g++-12 protobuf-compiler libprotobuf-dev     && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12

# 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     pytorch-cpu=2.1.2     torchvision-cpu=0.16.2    &&     micromamba clean --all --yes

COPY ./ /workspace/vllm

WORKDIR /workspace/vllm

# These packages will be in rocketce eventually
RUN pip install -v -r requirements-cpu.txt --prefer-binary --extra-index-url https://repo.fury.io/mgiessing

RUN VLLM_TARGET_DEVICE=cpu python3 setup.py install

WORKDIR /vllm-workspace
ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]