FROM intel/oneapi-basekit:2024.0.1-devel-ubuntu22.04

ARG http_proxy
ARG https_proxy

ENV TZ=Asia/Shanghai
ENV PYTHONUNBUFFERED=1
ENV USE_XETLA=OFF
ENV SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1

COPY chat.py /llm/chat.py

# Disable pip's cache behavior
ARG PIP_NO_CACHE_DIR=false

RUN curl -fsSL https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS-2023.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
    echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " > /etc/apt/sources.list.d/oneAPI.list && \
    apt-get update && \
    apt-get install -y curl wget git gnupg gpg-agent && \
    wget -qO - https://repositories.intel.com/graphics/intel-graphics.key | gpg --dearmor --output /usr/share/keyrings/intel-graphics.gpg && \
    echo 'deb [arch=amd64,i386 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/graphics/ubuntu jammy arc' | tee /etc/apt/sources.list.d/intel.gpu.jammy.list && \
    rm /etc/apt/sources.list.d/intel-graphics.list && \
    # Install PYTHON 3.9 and BigDL-LLM[xpu]
    ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone && \
    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 && \
    pip install --pre --upgrade bigdl-llm[xpu_2.1] -f https://developer.intel.com/ipex-whl-stable-xpu && \
    pip install transformers_stream_generator einops tiktoken && \
    # Install opencl-related repos
    apt-get update && \
    apt-get install -y intel-opencl-icd intel-level-zero-gpu=1.3.26241.33-647~22.04 level-zero level-zero-dev --allow-downgrades && \
    # Install related libary of chat.py
    pip install --upgrade colorama && \
    # Install vllm dependencies
    pip install --upgrade fastapi && \
    pip install --upgrade "uvicorn[standard]" && \
    # Download vLLM-Serving
    git clone https://github.com/intel-analytics/BigDL && \
    cp -r ./BigDL/python/llm/example/GPU/vLLM-Serving/ ./vLLM-Serving && \
    rm -rf ./BigDL