Dockerfile

FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04

WORKDIR /app

ENV PYTHONUNBUFFERED=1 PORT=7860 HF_HUB_OFFLINE=0

RUN apt-get update && apt-get install -y --no-install-recommends python3 python3-pip && rm -rf /var/lib/apt/lists/*

COPY requirements.txt .
RUN pip install --upgrade pip && pip install --no-cache-dir -r requirements.txt

COPY . .

EXPOSE 7860

HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/health')" || exit 1

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