Dockerfile

FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04

# System dependencies
RUN apt-get update && apt-get install -y \
    python3 python3-pip python3-dev \
    git git-lfs curl build-essential \
    && rm -rf /var/lib/apt/lists/*

RUN ln -sf /usr/bin/python3 /usr/bin/python

WORKDIR /app

# Install llama-cpp-python with CUDA support first — longest build step
RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python --no-cache-dir

# Install remaining requirements
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application files
COPY . .

# HuggingFace Spaces runs as non-root user 1000
RUN useradd -m -u 1000 user
RUN chown -R user:user /app
USER user

RUN mkdir -p /app/hf_cache

ENV HF_HOME=/app/hf_cache
ENV PYTHONUNBUFFERED=1

EXPOSE 7860

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