24 lines
758 B
Docker
24 lines
758 B
Docker
FROM intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT
|
|
|
|
ARG http_proxy
|
|
ARG https_proxy
|
|
ARG TINI_VERSION=v0.18.0
|
|
|
|
# Disable pip's cache behavior
|
|
ARG PIP_NO_CACHE_DIR=false
|
|
|
|
COPY ./entrypoint.sh /opt/entrypoint.sh
|
|
COPY ./model_adapter.py.patch /llm/model_adapter.py.patch
|
|
ADD https://github.com/krallin/tini/releases/download/${TINI_VERSION}/tini /sbin/tini
|
|
# Install Serving Dependencies
|
|
RUN cd /llm && \
|
|
pip install --pre --upgrade bigdl-llm[serving] && \
|
|
# Fix Qwen model adpater in fastchat
|
|
patch /usr/local/lib/python3.9/dist-packages/fastchat/model/model_adapter.py < /llm/model_adapter.py.patch && \
|
|
chmod +x /opt/entrypoint.sh && \
|
|
chmod +x /sbin/tini && \
|
|
cp /sbin/tini /usr/bin/tini
|
|
|
|
|
|
WORKDIR /llm/
|
|
ENTRYPOINT [ "/opt/entrypoint.sh" ]
|