hfdoc

# ARG CUDA_IMAGE="12.1.0-devel-ubuntu22.04"
# FROM nvidia/cuda:${CUDA_IMAGE}
FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04

# 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 hf_xet

# Install llama-cpp-python (build with cuda)
RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121

# # Run the server
# CMD python3 -m llama_cpp.server

# python -m llama_cpp.server --model /path/to/your/model.gguf --host 0.0.0.0 --port 8000
CMD ["python3", "-W","ignore","-m", "llama_cpp.server", "--hf_model_repo_id", "unsloth/Qwen3-30B-A3B-GGUF" ,"--model", "*Q4_0.gguf", "--host", "0.0.0.0", "--port", "8000"]