FROM docker.io/pytorch/pytorch:2.11.0-cuda12.8-cudnn9-runtime

# System dependencies for audio processing
RUN apt-get update && apt-get install -y --no-install-recommends \
    libsndfile1 \
    ffmpeg \
    && rm -rf /var/lib/apt/lists/*

# Install Python dependencies
COPY requirements.txt /tmp/requirements.txt
RUN pip install --no-cache-dir -r /tmp/requirements.txt && rm /tmp/requirements.txt

# llama-cpp-python needs CUDA build
RUN CMAKE_ARGS="-DGGML_CUDA=on" pip install --no-cache-dir --force-reinstall llama-cpp-python>=0.3.0

# Copy application code
COPY llmux/ /app/llmux/
WORKDIR /app

# Run the server
EXPOSE 8081
CMD ["uvicorn", "llmux.main:app", "--host", "0.0.0.0", "--port", "8081"]