@@ -310,6 +310,145 @@ jobs:
310310 with :
311311 key : release-${{ matrix.os }}-vulkan
312312
313+ ubuntu-cuda :
314+ name : ubuntu-cuda (${{ matrix.label }}, ${{ matrix.build }})
315+ needs : [check-release, ui-build]
316+ if : ${{ needs.check-release.outputs.should_release == 'true' }}
317+
318+ strategy :
319+ matrix :
320+ include :
321+ # label = short version used in artifact names / release body
322+ # cuda = full container image tag
323+ - build : ' x64'
324+ os : ubuntu-24.04
325+ cuda : ' 12.8.2'
326+ label : ' 12.8'
327+ defines : ' -DGGML_CUDA_CUB_3DOT2=ON'
328+ - build : ' x64'
329+ os : ubuntu-24.04
330+ cuda : ' 13.3.1'
331+ label : ' 13.3'
332+ defines : ' '
333+ - build : ' arm64'
334+ os : ubuntu-24.04-arm
335+ cuda : ' 13.3.1'
336+ label : ' 13.3'
337+ defines : ' '
338+
339+ runs-on : ${{ matrix.os }}
340+ container : nvidia/cuda:${{ matrix.cuda }}-devel-ubuntu24.04
341+
342+ permissions :
343+ actions : write
344+
345+ steps :
346+ # the container has no git; install it before checkout so that a real git
347+ # repository is created (the get-tag-name action and the build both need it)
348+ - name : Install git
349+ run : |
350+ apt-get update
351+ apt-get install -y --no-install-recommends git
352+
353+ - name : Clone
354+ id : checkout
355+ uses : actions/checkout@v6
356+ with :
357+ fetch-depth : 0
358+
359+ # checkout runs as the host user; in-container steps run as root, so git
360+ # refuses to touch a repo it does not own. Mark the workspace as safe.
361+ # use the env var: the github.workspace context holds the HOST path,
362+ # GITHUB_WORKSPACE the container path
363+ - name : Git safe directory
364+ run : git config --global --add safe.directory "$GITHUB_WORKSPACE"
365+
366+ - name : Download UI build
367+ uses : actions/download-artifact@v7
368+ with :
369+ name : llama-ui.zip
370+ path : tools/ui/dist
371+
372+ - name : Dependencies
373+ id : depends
374+ # container jobs default to sh (dash); need bash for the [[ ]] below
375+ shell : bash
376+ run : |
377+ apt-get update
378+ apt-get install -y --no-install-recommends build-essential cmake ninja-build libssl-dev jq python3-venv
379+ # the container ships GCC 13, which does not know the 'sme' march
380+ # feature used by the armv9.2 CPU variant of GGML_CPU_ALL_VARIANTS
381+ if [[ "${{ matrix.build }}" == "arm64" ]]; then
382+ apt-get install -y --no-install-recommends gcc-14 g++-14
383+ echo "CC=gcc-14" >> "$GITHUB_ENV"
384+ echo "CXX=g++-14" >> "$GITHUB_ENV"
385+ fi
386+
387+ - name : ccache
388+ uses : ggml-org/ccache-action@v1.2.24
389+ with :
390+ key : release-ubuntu-${{ matrix.os }}-cuda-${{ matrix.label }}-${{ matrix.build }}
391+ evict-old-files : 1d
392+ max-size : " 1G"
393+
394+ - name : Build
395+ id : cmake_build
396+ # no CMAKE_CUDA_ARCHITECTURES: use the broad default arch set from
397+ # ggml/src/ggml-cuda/CMakeLists.txt so the release binary covers many GPUs
398+ run : |
399+ cmake -B build \
400+ -DCMAKE_INSTALL_RPATH='$ORIGIN' \
401+ -DCMAKE_BUILD_WITH_INSTALL_RPATH=ON \
402+ -DGGML_BACKEND_DL=ON \
403+ -DGGML_NATIVE=OFF \
404+ -DGGML_CPU_ALL_VARIANTS=ON \
405+ -DGGML_CUDA=ON \
406+ -DGGML_CUDA_NCCL=OFF \
407+ ${{ env.CMAKE_ARGS }} ${{ matrix.defines }}
408+ cmake --build build --config Release -j $(nproc)
409+
410+ - name : Determine tag name
411+ id : tag
412+ uses : ./.github/actions/get-tag-name
413+
414+ - name : Pack artifacts
415+ id : pack_artifacts
416+ run : |
417+ cp LICENSE ./build/bin/
418+ tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz --transform "s,^\.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .
419+
420+ - name : Upload artifacts
421+ uses : actions/upload-artifact@v6
422+ with :
423+ path : llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz
424+ name : llama-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz
425+
426+ # ship the CUDA runtime libraries the backend links against, mirroring
427+ # the windows-cuda cudart zip - extract next to the binaries ($ORIGIN rpath)
428+ - name : Pack CUDA runtime
429+ id : pack_cuda_runtime
430+ run : |
431+ major="${{ matrix.label }}"
432+ major="${major%%.*}"
433+ mkdir -p ./cudart
434+ # cp -L dereferences the SONAME symlinks into plain files, so the
435+ # tarball holds exactly 3 files with no versioned duplicates
436+ cp -L /usr/local/cuda/lib64/libcudart.so.${major} ./cudart/
437+ cp -L /usr/local/cuda/lib64/libcublas.so.${major} ./cudart/
438+ cp -L /usr/local/cuda/lib64/libcublasLt.so.${major} ./cudart/
439+ 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 .
440+
441+ - name : Upload CUDA runtime
442+ uses : actions/upload-artifact@v6
443+ with :
444+ path : cudart-llama-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz
445+ name : cudart-llama-bin-ubuntu-cuda-${{ matrix.label }}-${{ matrix.build }}.tar.gz
446+
447+ - name : ccache-clear
448+ uses : ./.github/actions/ccache-clear
449+ with :
450+ key : release-ubuntu-${{ matrix.os }}-cuda-${{ matrix.label }}-${{ matrix.build }}
451+
313452 android-arm64 :
314453 needs : [check-release, ui-build]
315454 if : ${{ needs.check-release.outputs.should_release == 'true' }}
@@ -1572,6 +1711,7 @@ jobs:
15721711 - ubuntu-24-rocm
15731712 - ubuntu-cpu
15741713 - ubuntu-vulkan
1714+ - ubuntu-cuda
15751715 - ubuntu-24-openvino
15761716 - ubuntu-24-sycl
15771717 - android-arm64
@@ -1703,6 +1843,9 @@ jobs:
17031843 - [Ubuntu s390x (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-s390x.tar.gz)
17041844 - [Ubuntu x64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-x64.tar.gz)
17051845 - [Ubuntu arm64 (Vulkan)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-arm64.tar.gz)
1846+ - [Ubuntu x64 (CUDA 12)](https://github.com/ggml-org/llama.cpp/releases/download/${{ 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-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-12.8-x64.tar.gz)
1847+ - [Ubuntu x64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ 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-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-x64.tar.gz)
1848+ - [Ubuntu arm64 (CUDA 13)](https://github.com/ggml-org/llama.cpp/releases/download/${{ 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-${{ steps.tag.outputs.name }}-bin-ubuntu-cuda-13.3-arm64.tar.gz)
17061849 - [Ubuntu x64 (ROCm 10.0)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-10.0-x64.tar.gz)
17071850 - [Ubuntu x64 (OpenVINO)](https://github.com/ggml-org/llama.cpp/releases/download/${{ steps.tag.outputs.name }}/llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ needs.ubuntu-24-openvino.outputs.openvino_version }}-x64.tar.gz)
17081851 - [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)
0 commit comments