Dockerfile.neuron

# default base image
ARG BASE_IMAGE="public.ecr.aws/neuron/pytorch-inference-neuronx:2.1.2-neuronx-py310-sdk2.20.0-ubuntu20.04"

FROM $BASE_IMAGE

RUN echo "Base image is $BASE_IMAGE"

# Install some basic utilities
RUN apt-get update && \
    apt-get install -y \
        git \
        python3 \
        python3-pip \
        ffmpeg libsm6 libxext6 libgl1

### Mount Point ###
# When launching the container, mount the code directory to /app
ARG APP_MOUNT=/app
VOLUME [ ${APP_MOUNT} ]
WORKDIR ${APP_MOUNT}/vllm

RUN python3 -m pip install --upgrade pip
RUN python3 -m pip install --no-cache-dir fastapi ninja tokenizers pandas
RUN python3 -m pip install sentencepiece transformers==4.36.2 -U
RUN python3 -m pip install transformers-neuronx --extra-index-url=https://pip.repos.neuron.amazonaws.com -U
RUN python3 -m pip install --pre neuronx-cc==2.15.* --extra-index-url=https://pip.repos.neuron.amazonaws.com -U

COPY . .
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 python3 -m pip install -U \
        cmake>=3.26 ninja packaging setuptools-scm>=8 wheel jinja2 \
        -r requirements-neuron.txt

ENV VLLM_TARGET_DEVICE neuron
RUN --mount=type=bind,source=.git,target=.git \
    pip install --no-build-isolation -v -e . \

CMD ["/bin/bash"]