ipex-llm/docker/llm/inference/cpu/docker/Dockerfile
2024-02-05 09:06:59 +08:00

73 lines
No EOL
3.3 KiB
Docker

FROM ubuntu:22.04
ARG http_proxy
ARG https_proxy
ARG PIP_NO_CACHE_DIR=false
ARG DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
COPY ./start-notebook.sh /llm/start-notebook.sh
# Install PYTHON 3.9
RUN env DEBIAN_FRONTEND=noninteractive apt-get update && \
apt install software-properties-common libunwind8-dev vim less -y && \
add-apt-repository ppa:deadsnakes/ppa -y && \
apt-get install -y python3.9 git curl wget && \
rm /usr/bin/python3 && \
ln -s /usr/bin/python3.9 /usr/bin/python3 && \
ln -s /usr/bin/python3 /usr/bin/python && \
apt-get install -y python3-pip python3.9-dev python3-wheel python3.9-distutils && \
curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
# Install FastChat from source requires PEP 660 support
python3 get-pip.py && \
rm get-pip.py && \
pip install --upgrade requests argparse urllib3 && \
pip3 install --no-cache-dir --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu && \
pip install --pre --upgrade bigdl-llm[all] && \
# Download bigdl-llm-tutorial
cd /llm && \
pip install --upgrade jupyterlab && \
git clone https://github.com/intel-analytics/bigdl-llm-tutorial && \
chmod +x /llm/start-notebook.sh && \
# Download all-in-one benchmark
git clone https://github.com/intel-analytics/BigDL && \
cp -r ./BigDL/python/llm/dev/benchmark/ ./benchmark && \
# Copy chat.py script
pip install --upgrade colorama && \
cp -r ./BigDL/python/llm/portable-zip/ ./portable-zip && \
# Install all-in-one dependencies
apt-get install -y numactl && \
pip install --upgrade omegaconf && \
pip install --upgrade pandas && \
# Install vllm dependencies
pip install --upgrade fastapi && \
pip install --upgrade "uvicorn[standard]" && \
# Add Qwen support
pip install --upgrade transformers_stream_generator einops && \
# Copy vLLM-Serving
cp -r ./BigDL/python/llm/example/CPU/vLLM-Serving/ ./vLLM-Serving && \
rm -rf ./BigDL && \
# Install miniconda
curl -LO "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh" && \
bash Miniconda3-latest-Linux-x86_64.sh -b && \
rm -f Miniconda3-latest-Linux-x86_64.sh && \
# Install environment for speculative
/root/miniconda3/condabin/conda init bash && \
/bin/bash -c "source /root/.bashrc" && \
/root/miniconda3/condabin/conda create -n bigdl-speculative-py39 -y python=3.9
SHELL ["/root/miniconda3/condabin/conda", "run", "-n", "bigdl-speculative-py39", "/bin/bash", "-c"]
RUN cd /llm && \
pip3 install --no-cache-dir --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu && \
pip install --pre --upgrade bigdl-llm[all] && \
wget https://raw.githubusercontent.com/intel/intel-extension-for-pytorch/0c63936d7a6740679987920367ae2e0cdb375b2e/scripts/compile_bundle.sh && \
sed -i 's/VER_IPEX=main/VER_IPEX=0c63936d7a6740679987920367ae2e0cdb375b2e/g' "compile_bundle.sh" && \
bash compile_bundle.sh && \
cd ./intel-extension-for-pytorch && \
pip install -r requirements.txt && \
pip install transformers==4.36.2 && \
pip install transformers_stream_generator && \
rm -rf llvm-project llvm-release intel-extension-for-pytorch compile_bundle.sh && \
echo "conda deactivate" >> /root/.bashrc
ENTRYPOINT ["/bin/bash"]