ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Add all-in-one benchmark into inference-cpu docker image (#9433)

Browse source 
* add all-in-one into inference-cpu image

* manually_build

* revise files
This commit is contained in:
Lilac09 2023-11-13 13:07:56 +08:00 committed by GitHub
parent 9b5d0e9c75
commit 5d4ec44488
1 changed files with 9 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
docker/llm/inference/cpu/docker/Dockerfile
View file

@ -33,6 +33,14 @@ RUN env DEBIAN_FRONTEND=noninteractive apt-get update && \
chmod +x /llm/start-notebook.sh && \
# Download chat.py script
pip install --upgrade colorama && \
wget -P /llm https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/portable-zip/chat.py
wget -P /llm https://raw.githubusercontent.com/intel-analytics/BigDL/main/python/llm/portable-zip/chat.py && \
# Download all-in-one benchmark
git clone https://github.com/intel-analytics/BigDL && \
cp -r ./BigDL/python/llm/dev/benchmark/ ./benchmark && \
rm -rf ./BigDL && \
# Install all-in-one dependencies
apt-get install -y numactl && \
pip install --upgrade omegaconf && \
pip install --upgrade pandas
ENTRYPOINT ["/bin/bash"]