Dockerfile.cuda

ARG CUDA_VERSION=12.6.3
ARG UBUNTU_VERSION=24.04

FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu${UBUNTU_VERSION} AS build

RUN apt-get update && apt-get install -y --no-install-recommends build-essential git ccache cmake

WORKDIR /sd.cpp

COPY . .

ARG CUDACXX=/usr/local/cuda/bin/nvcc
ARG CUDA_ARCHITECTURES=""
ARG GGML_CUDA_FA_ALL_QUANTS=""

RUN cmake . -B ./build \
    -DSD_CUDA=ON \
    ${CUDA_ARCHITECTURES:+-DCMAKE_CUDA_ARCHITECTURES="${CUDA_ARCHITECTURES}"} \
    ${GGML_CUDA_FA_ALL_QUANTS:+-DGGML_CUDA_FA_ALL_QUANTS=${GGML_CUDA_FA_ALL_QUANTS}}
RUN cmake --build ./build --config Release -j$(nproc)

FROM nvidia/cuda:${CUDA_VERSION}-cudnn-runtime-ubuntu${UBUNTU_VERSION} AS runtime

RUN apt-get update && \
    apt-get install --yes --no-install-recommends libgomp1 && \
    apt-get clean

COPY --from=build /sd.cpp/build/bin/sd-cli /sd-cli
COPY --from=build /sd.cpp/build/bin/sd-server /sd-server

ENTRYPOINT [ "/sd-cli" ]