Dockerfile

FROM python:3.11-slim AS runtime
ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PORT=7860 \
    GRADIO_SERVER_NAME=0.0.0.0

RUN apt-get update \
    && apt-get install -y --no-install-recommends ca-certificates libcurl4 libgomp1 libstdc++6 git \
    && rm -rf /var/lib/apt/lists/*

RUN echo '#!/bin/sh' > /usr/local/bin/llama-server && \
    echo 'python -m llama_cpp.server "$@"' >> /usr/local/bin/llama-server && \
    chmod +x /usr/local/bin/llama-server
RUN echo '#!/bin/sh' > /usr/local/bin/llama-cli && \
    echo 'python -m llama_cpp.cli "$@"' >> /usr/local/bin/llama-cli && \
    chmod +x /usr/local/bin/llama-cli

RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"

WORKDIR /app

COPY --chown=user requirements.txt ./requirements.txt
RUN python -m pip install --no-cache-dir --upgrade pip setuptools wheel \
    && python -m pip install --no-cache-dir -r requirements.txt

COPY --chown=user . /app

ARG HF_TOKEN
ENV HF_TOKEN=${HF_TOKEN}
RUN pip install huggingface_hub hf_transfer
USER root
RUN mkdir -p /data && chown -R user:user /data
USER user
RUN python scripts/download_gguf.py openbmb/MiniCPM5-1B-GGUF MiniCPM5-1B-Q4_K_M.gguf models/MiniCPM5-1B-Q4_K_M.gguf

EXPOSE 7860 8080
CMD ["python", "app.py"]