FROM ghcr.io/ggml-org/llama.cpp:server-cuda

ENV MODEL_REPO=mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF
ENV MODEL_FILE=NVIDIA-Nemotron-3-Nano-4B-BF16.Q4_K_M.gguf
ENV PORT=7860
ENV CTX_SIZE=2048
ENV N_GPU_LAYERS=99
ENV NO_WARMUP=1
ENV HF_XET_HIGH_PERFORMANCE=1

USER root
RUN apt-get update \
    && apt-get install -y --no-install-recommends python3 python3-pip ca-certificates \
    && rm -rf /var/lib/apt/lists/* \
    && python3 -m pip install --break-system-packages --no-cache-dir "huggingface_hub"

COPY start_server.py /app/start_server.py

EXPOSE 7860
ENTRYPOINT []
CMD ["python3", "/app/start_server.py"]