ARM Runners support CUDA SBSA

.github/workflows/build-and-release.yaml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-22.04, windows-2022, macos-14, macos-15]
+        os: [ubuntu-22.04, ubuntu-22.04-arm, windows-2022, macos-13, macos-15]
 
     steps:
       - uses: actions/checkout@v4
@@ -42,7 +42,7 @@ jobs:
         shell: cmd
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.22.0
+        uses: pypa/cibuildwheel@v3.0.0
         env:
           # disable repair
           CIBW_REPAIR_WHEEL_COMMAND: ""
@@ -55,36 +55,6 @@ jobs:
           name: wheels-${{ matrix.os }}
           path: ./wheelhouse/*.whl
 
-  build_wheels_arm64:
-    name: Build arm64 wheels
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: "recursive"
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          platforms: linux/arm64
-
-      - name: Build wheels
-        uses: pypa/cibuildwheel@v2.22.0
-        env:
-          CIBW_SKIP: "*musllinux* pp*"
-          CIBW_REPAIR_WHEEL_COMMAND: ""
-          CIBW_ARCHS: "aarch64"
-          CIBW_ENVIRONMENT: CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DCMAKE_CROSSCOMPILING=ON"
-          CIBW_BUILD: "cp38-* cp39-* cp310-* cp311-* cp312-*"
-        with:
-          output-dir: wheelhouse
-
-      - name: Upload wheels as artifacts
-        uses: actions/upload-artifact@v4
-        with:
-          name: wheels_arm64
-          path: ./wheelhouse/*.whl
-
   build_sdist:
     name: Build source distribution
     runs-on: ubuntu-latest
@@ -129,7 +99,7 @@ jobs:
 
   release:
     name: Release
-    needs: [build_wheels, build_wheels_arm64, build_sdist]
+    needs: [build_wheels, build_sdist]
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/build-docker.yaml

@@ -9,19 +9,16 @@ permissions:
 jobs:
   docker:
     name: Build and push Docker image
-    runs-on: ubuntu-22.04
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: ["ubuntu-latest", "ubuntu-24.04-arm"]
     steps:
       - name: Checkout
         uses: actions/checkout@v4
         with:
           submodules: "recursive"
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
+
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3 
         with:

.github/workflows/build-wheels-cuda.yaml

@@ -20,9 +20,9 @@ jobs:
         id: set-matrix
         run: |
           $matrix = @{
-              'os' = @('ubuntu-22.04') #, 'windows-2022')
-              'pyver' = @("3.9", "3.10", "3.11", "3.12")
-              'cuda' = @("12.1.1", "12.2.2", "12.3.2", "12.4.1") #, "12.5.1", "12.6.1")
+              'os' = @('ubuntu-22.04', 'ubuntu-22.04-arm', 'windows-2022')
+              'pyver' = @("3.10", "3.11", "3.12", "3.13")
+              'cuda' = @("12.6.3", "12.8.1", "12.9.1") #, "12.5.1", "12.6.1")
               'releasetag' = @("basic")
           }
 
@@ -47,7 +47,7 @@ jobs:
         if: runner.os == 'Windows'
         uses: microsoft/setup-msbuild@v2
         with:
-          vs-version: '[16.11,16.12)'
+          vs-version: 'latest'
 
       - uses: actions/checkout@v4
         with:
@@ -59,7 +59,7 @@ jobs:
           cache: 'pip'
 
       - name: Setup Mamba
-        uses: conda-incubator/setup-miniconda@v3.1.0
+        uses: conda-incubator/setup-miniconda@v3.2.0
         with:
           activate-environment: "llamacpp"
           python-version: ${{ matrix.pyver }}
@@ -89,7 +89,7 @@ jobs:
         if: runner.os == 'Windows'
         run: |
           $y = (gi '.\MSBuildExtensions').fullname + '\*'
-          (gi 'C:\Program Files (x86)\Microsoft Visual Studio\2019\Enterprise\MSBuild\Microsoft\VC\*\BuildCustomizations').fullname.foreach({cp $y $_})
+          (gi 'C:\Program Files\Microsoft Visual Studio\2022\Enterprise\MSBuild\Microsoft\VC\*\BuildCustomizations').fullname.foreach({cp $y $_})
           $cupath = 'CUDA_PATH_V' + $env:CUDAVER.Remove($env:CUDAVER.LastIndexOf('.')).Replace('.','_')
           echo "$cupath=$env:CONDA_PREFIX" >> $env:GITHUB_ENV
 

.github/workflows/test.yaml

@@ -31,10 +31,11 @@ jobs:
 
   build-linux:
     needs: download-model
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        os: ["ubuntu-latest", "ubuntu-24.04-arm"]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
     steps:
       - uses: actions/checkout@v4
         with: