Dockerfile

# Dockerfile
FROM python:3.11-slim

ENV PYTHONUNBUFFERED=1 \
    CMAKE_ARGS="-DLLAMA_AVX2=ON -DLLAMA_AVX=ON -DLLAMA_FMA=ON" \
    FORCE_CMAKE=1

# System deps for llama.cpp compilation
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    cmake \
    git \
    wget \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

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

COPY app/ ./app/

EXPOSE 7860

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]