Dockerfile

ARG CUDA_IMAGE="12.5.0-devel-ubuntu22.04"
FROM nvidia/cuda:${CUDA_IMAGE}

# We need to set the host to 0.0.0.0 to allow outside access
ENV HOST 0.0.0.0

RUN apt-get update && apt-get upgrade -y \
    && apt-get install -y git build-essential \
    python3 python3-pip gcc wget \
    ocl-icd-opencl-dev opencl-headers clinfo \
    libclblast-dev libopenblas-dev \
    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd

# ちゃんと書き込みできるユーザー設定しないとエラーが出るっぽい。
RUN useradd -m -u 1000 gee
USER gee
ENV HOME=/home/gee \
    PATH=/home/gee/.local/bin:$PATH

ENV HF_HOME=$HOME/app/.cache/huggingface
WORKDIR $HOME/app


COPY --chown=gee . $HOME/app

# setting build related env vars
ENV CUDA_DOCKER_ARCH=all
ENV GGML_CUDA=1

# Install depencencies
RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context huggingface-hub

RUN python3 -m pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu125
# Install llama-cpp-python (build with cuda)
# RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python

# Run the server
CMD ["python3", "llm.py"]