diff --git a/.github/workflows/compile.yml b/.github/workflows/compile.yml index 51691dfc4..f08920724 100644 --- a/.github/workflows/compile.yml +++ b/.github/workflows/compile.yml @@ -405,7 +405,12 @@ jobs: fail-fast: false matrix: os: [ubuntu-22.04, windows-2022] - cuda: ['12.4.0'] + cuda: ['12.4.0', '13.0.0'] + include: + - cuda: '12.4.0' + win-sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]' + - cuda: '13.0.0' + win-sub-packages: '["nvcc", "crt", "nvvm", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]' runs-on: ${{ matrix.os }} steps: - name: Clone @@ -416,15 +421,15 @@ jobs: fetch-depth: 0 ref: '${{ github.event.inputs.llama_cpp_commit }}' - - uses: Jimver/cuda-toolkit@v0.2.15 + - uses: Jimver/cuda-toolkit@v0.2.36 if: runner.os == 'Windows' id: cuda-toolkit-windows with: cuda: ${{ matrix.cuda }} method: 'network' - sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]' + sub-packages: ${{ matrix.win-sub-packages }} - - uses: Jimver/cuda-toolkit@v0.2.15 + - uses: Jimver/cuda-toolkit@v0.2.36 if: runner.os == 'Linux' id: cuda-toolkit-linux with: @@ -688,7 +693,7 @@ jobs: - name: Rearrange Files run: | # Make all directories at once - mkdir --parents deps/{noavx,avx,avx2,avx512,linux-arm64,musl-noavx,musl-avx,musl-avx2,musl-avx512,osx-arm64,osx-x64,osx-x64-rosetta2,cu12.4.0,vulkan,android-arm64-v8a,android-x86,android-x86_64,win-arm64} + mkdir --parents deps/{noavx,avx,avx2,avx512,linux-arm64,musl-noavx,musl-avx,musl-avx2,musl-avx512,osx-arm64,osx-x64,osx-x64-rosetta2,cu12.4.0,cu13.0.0,vulkan,android-arm64-v8a,android-x86,android-x86_64,win-arm64} # Linux cp artifacts/ggml-bin-linux-noavx-x64.so/libggml.so deps/noavx/libggml.so @@ -821,6 +826,12 @@ jobs: cp artifacts/llama-bin-win-cublas-cu12.4.0-x64.dll/llama.dll deps/cu12.4.0/llama.dll cp artifacts/mtmd-bin-win-cublas-cu12.4.0-x64.dll/mtmd.dll deps/cu12.4.0/mtmd.dll + cp artifacts/ggml-bin-win-cublas-cu13.0.0-x64.dll/ggml.dll deps/cu13.0.0/ggml.dll + cp artifacts/ggml-base-bin-win-cublas-cu13.0.0-x64.dll/ggml-base.dll deps/cu13.0.0/ggml-base.dll + cp artifacts/ggml-cuda-bin-win-cublas-cu13.0.0-x64.dll/ggml-cuda.dll deps/cu13.0.0/ggml-cuda.dll + cp artifacts/llama-bin-win-cublas-cu13.0.0-x64.dll/llama.dll deps/cu13.0.0/llama.dll + cp artifacts/mtmd-bin-win-cublas-cu13.0.0-x64.dll/mtmd.dll deps/cu13.0.0/mtmd.dll + # Linux CUDA cp artifacts/ggml-bin-linux-cublas-cu12.4.0-x64.so/libggml.so deps/cu12.4.0/libggml.so cp artifacts/ggml-base-bin-linux-cublas-cu12.4.0-x64.so/libggml-base.so deps/cu12.4.0/libggml-base.so @@ -828,6 +839,12 @@ jobs: cp artifacts/llama-bin-linux-cublas-cu12.4.0-x64.so/libllama.so deps/cu12.4.0/libllama.so cp artifacts/mtmd-bin-linux-cublas-cu12.4.0-x64.so/libmtmd.so deps/cu12.4.0/libmtmd.so + cp artifacts/ggml-bin-linux-cublas-cu13.0.0-x64.so/libggml.so deps/cu13.0.0/libggml.so + cp artifacts/ggml-base-bin-linux-cublas-cu13.0.0-x64.so/libggml-base.so deps/cu13.0.0/libggml-base.so + cp artifacts/ggml-cuda-bin-linux-cublas-cu13.0.0-x64.so/libggml-cuda.so deps/cu13.0.0/libggml-cuda.so + cp artifacts/llama-bin-linux-cublas-cu13.0.0-x64.so/libllama.so deps/cu13.0.0/libllama.so + cp artifacts/mtmd-bin-linux-cublas-cu13.0.0-x64.so/libmtmd.so deps/cu13.0.0/libmtmd.so + # Windows Vulkan cp artifacts/ggml-bin-win-vulkan-x64.dll/ggml.dll deps/vulkan/ggml.dll cp artifacts/ggml-base-bin-win-vulkan-x64.dll/ggml-base.dll deps/vulkan/ggml-base.dll