ARG CUDA_IMAGE="12.4.1-cudnn-devel-ubuntu22.04" FROM nvidia/cuda:${CUDA_IMAGE} # We need to set the host to 0.0.0.0 to allow outside access ENV HOST 0.0.0.0 RUN apt-get update && apt-get upgrade -y \ && apt-get install -y git build-essential \ python3 python3-pip gcc wget \ ocl-icd-opencl-dev opencl-headers clinfo \ libclblast-dev libopenblas-dev \ && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd COPY . . # setting build related env vars ENV CUDA_DOCKER_ARCH=all ENV LLAMA_CUBLAS=1 # Install depencencies RUN python3 -m pip install --upgrade pip pytest cmake \ scikit-build setuptools fastapi uvicorn sse-starlette \ pydantic-settings starlette-context gradio huggingface_hub[hf_transfer] hf_transfer # Install llama-cpp-python (build with cuda) RUN pip install llama-cpp-python \ --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124 RUN useradd -m -u 1000 user # Switch to the "user" user USER user # Set home to the user's home directory ENV HOME=/home/user \ PATH=/home/user/.local/bin:$PATH \ PYTHONPATH=$HOME/app \ PYTHONUNBUFFERED=1 \ GRADIO_ALLOW_FLAGGING=never \ GRADIO_NUM_PORTS=1 \ GRADIO_SERVER_NAME=0.0.0.0 \ GRADIO_THEME=huggingface \ SYSTEM=spaces \ HF_HUB_ENABLE_HF_TRANSFER=1 WORKDIR $HOME/app # Copy the current directory contents into the container at $HOME/app setting the owner to the user COPY --chown=user . $HOME/app CMD ["python3", "app.py"]