Files
enginex-bi_series-vllm/Dockerfile

16 lines
626 B
Docker

FROM git.modelhub.org.cn:9443/enginex-iluvatar/bi100-3.2.3-x86-ubuntu20.04-py3.10-poc-llm-infer:v1.2.3
RUN pip install --no-cache-dir triton==2.1.0
COPY pkgs/triton /usr/local/corex/lib64/python3/dist-packages/triton
COPY pkgs/triton-2.1.0+corex.4.1.2.dist-info /usr/local/corex/lib64/python3/dist-packages/triton-2.1.0+corex.4.1.2.dist-info
COPY paged_attn.py /usr/local/corex/lib64/python3/dist-packages/vllm/attention/ops/paged_attn.py
COPY __init__.py /usr/local/corex/lib64/python3/dist-packages/vllm/triton_utils/__init__.py
RUN mkdir /workspace
WORKDIR /workspace/
COPY ./launch_service /workspace/launch_service