LLM inference in C/C++
C++ ggml
ci : add ubuntu-cuda builds to release (#28186)
Oliver Simons391fac16460f
diff --git a/.github/workflows/release.yml b/.github/workflows/release.ymlindex 91dcbe48be..be36b04326 100644--- a/.github/workflows/release.yml+++ b/.github/workflows/release.yml@@ -310,6 +310,145 @@ jobs:with:key: release-${{ matrix.os }}-vulkan+ ubuntu-cuda:+ name: ubuntu-cuda (${{ matrix.label }}, ${{ matrix.build }})+ needs: [check-release, ui-build]+ if: ${{ needs.check-release.outputs.should_release == 'true' }}++ strategy:+ matrix:+ include:+ # label = short version used in artifact names / release body+ # cuda = full container image tag+ - build: 'x64'+ os: ubuntu-24.04+ cuda: '12.8.2'+ label: '12.8'+ defines: '-DGGML_CUDA_CUB_3DOT2=ON'+ - build: 'x64'+ os: ubuntu-24.04+ cuda: '13.3.1'+ label: '13.3'+ defines: ''+ - build: 'arm64'+ os: ubuntu-24.04-arm+ cuda: '13.3.1'+ label: '13.3'+ defines: ''++ runs-on: ${{ matrix.os }}+ container: nvidia/cuda:${{ matrix.cuda }}-devel-ubuntu24.04++ permissions:+ actions: write++ steps:+ # the container has no git; install it before checkout so that a real git+ # repository is created (the get-tag-name action and the build both need it)+ - name: Install git+ run: |+ apt-get update+ apt-get install -y --no-install-recommends git++ - name: Clone+ id: checkout+ uses: actions/checkout@v6+ with:+ fetch-depth: 0++ # checkout runs as the host user; in-container steps run as root, so git+ # refuses to touch a repo it does not own. Mark the workspace as safe.+ # use the env var: the github.workspace context holds the HOST path,+ # GITHUB_WORKSPACE the container path+ - name: Git safe directory+ run: git config --global --add safe.directory "$GITHUB_WORKSPACE"++ - name: Download UI build+ uses: actions/download-artifact@v7+ with:+ name: llama-ui.zip+ path: tools/ui/dist++ - name: Dependencies+ id: depends+ # container jobs default to sh (dash); need bash for the [[ ]] below+ shell: bash+ run: |+ apt-get update+ apt-get install -y --no-install-recommends build-essential cmake ninja-build libssl-dev jq python3-venv+ # the container ships GCC 13, which does not know the 'sme' march+ # feature used by the armv9.2 CPU variant of GGML_CPU_ALL_VARIANTS+ if [[ "${{ matrix.build }}" == "arm64" ]]; then+ apt-get install -y --no-install-recommends gcc-14 g++-14+ echo "CC=gcc-14" >> "$GITHUB_ENV"+ echo "CXX=g++-14" >> "$GITHUB_ENV"+ fi++ - name: ccache+ uses: ggml-org/[email protected]+ with:+ key: release-ubuntu-${{ matrix.os }}-cuda-${{ matrix.label }}-${{ matrix.build }}+ evict-old-files: 1d+ max-size: "1G"++ - name: Build+ id: cmake_build+ # no CMAKE_CUDA_ARCHITECTURES: use the broad default arch set from+ # ggml/src/ggml-cuda/CMakeLists.txt so the release binary covers many GPUs+ run: |+ cmake -B build \+ -DCMAKE_INSTALL_RPATH='$ORIGIN' \+ -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \+ -DGGML_BACKEND_DL=ON \+ -DGGML_NATIVE=OFF \+ -DGGML_CPU_ALL_VARIANTS=ON \+ -DGGML_CUDA=ON \+ -DGGML_CUDA_NCCL=OFF \+ ${{ env.CMAKE_ARGS }} ${{ matrix.defines }}+ cmake --build build --config Release -j $(nproc)++ - name: Determine tag name+ id: tag+ uses: ./.github/actions/get-tag-name++ - name: Pack artifacts+ id: pack_artifacts+ run: |+ cp LICENSE ./build/bin/+ tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz --transform "s,^\.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .++ - name: Upload artifacts+ uses: actions/upload-artifact@v6+ with:+ path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz+ name: llama-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz++ # ship the CUDA runtime libraries the backend links against, mirroring+ # the windows-cuda cudart zip - extract next to the binaries ($ORIGIN rpath)+ - name: Pack CUDA runtime+ id: pack_cuda_runtime+ run: |+ major="${{ matrix.label }}"+ major="${major%%.*}"+ mkdir -p ./cudart+ # cp -L dereferences the SONAME symlinks into plain files, so the+ # tarball holds exactly 3 files with no versioned duplicates+ cp -L /usr/local/cuda/lib64/libcudart.so.${major} ./cudart/+ cp -L /usr/local/cuda/lib64/libcublas.so.${major} ./cudart/+ cp -L /usr/local/cuda/lib64/libcublasLt.so.${major} ./cudart/+ tar -czvf cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz --transform "s,^\.,cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}," -C ./cudart .++ - name: Upload CUDA runtime+ uses: actions/upload-artifact@v6+ with:+ path: cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz+ name: cudart-llama-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz++ - name: ccache-clear+ uses: ./.github/actions/ccache-clear+ with:+ key: release-ubuntu-${{ matrix.os }}-cuda-${{ matrix.label }}-${{ matrix.build }}+android-arm64:needs: [check-release, ui-build]if: ${{ needs.check-release.outputs.should_release == 'true' }}@@ -1572,6 +1711,7 @@ jobs:- ubuntu-24-rocm- ubuntu-cpu- ubuntu-vulkan+ - ubuntu-cuda- ubuntu-24-openvino- ubuntu-24-sycl- android-arm64@@ -1703,6 +1843,9 @@ jobs:- [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-s390x.tar.gz)- [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.tar.gz)- [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-arm64.tar.gz)+ - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz) - [CUDA 12.8 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz)+ - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-x64.tar.gz) - [CUDA 13.3 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-x64.tar.gz)+ - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-arm64.tar.gz) - [CUDA 13.3 libraries](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-arm64.tar.gz)- [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-10.0-x64.tar.gz)- [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ needs.ubuntu-24-openvino.outputs.openvino_version }}-x64.tar.gz)- [Ubuntu x64 (SYCL FP32)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-fp32-x64.tar.gz)