Dockerfile

FROM ubuntu:22.04

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1

# ── 系统依赖 ──────────────────────────────────────────────────
RUN apt-get update && apt-get install -y \
    python3 python3-pip wget curl git \
    cmake build-essential libcurl4-openssl-dev \
    && rm -rf /var/lib/apt/lists/*

# ── 编译安装 llama.cpp（CPU，启用全部优化） ────────────────────
RUN git clone https://github.com/ggml-org/llama.cpp /llama.cpp && \
    cd /llama.cpp && \
    cmake -B build \
        -DGGML_NATIVE=ON \
        -DGGML_AVX2=ON \
        -DLLAMA_CURL=ON \
        -DCMAKE_BUILD_TYPE=Release && \
    cmake --build build --config Release -j$(nproc) && \
    cp build/bin/llama-server /usr/local/bin/llama-server && \
    rm -rf /llama.cpp

# ── Python 依赖 ────────────────────────────────────────────────
COPY requirements.txt /app/requirements.txt
RUN pip3 install --no-cache-dir -r /app/requirements.txt

# ── 应用代码 ───────────────────────────────────────────────────
COPY app.py /app/app.py
WORKDIR /app

# HF Spaces 要求端口 7860
EXPOSE 7860

CMD ["python3", "app.py"]