feat: support sgl-kernel cu129 (#8800)

.github/workflows/pr-test-sgl-kernel.yml

@@ -39,7 +39,7 @@ jobs:
           - python-version: '3.9'
             cuda-version: '12.4'
           - python-version: '3.9'
-            cuda-version: '12.8'
+            cuda-version: '12.9'
     name: Build Wheel (CUDA ${{ matrix.cuda-version }})
     steps:
       - name: Cleanup
@@ -56,7 +56,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: Build wheel for Python ${{ matrix.python-version }} and CUDA ${{ matrix.cuda-version }}
-        if: github.event_name != 'push' || (matrix.cuda-version != '11.8' && matrix.cuda-version != '12.8')
+        if: github.event_name != 'push' || (matrix.cuda-version != '11.8' && matrix.cuda-version != '12.9')
         run: |
           cd sgl-kernel
           chmod +x ./build.sh

.github/workflows/release-whl-kernel.yml

@@ -46,10 +46,89 @@ jobs:
           pip install twine
           python3 -m twine upload dist/* -u __token__ -p ${{ secrets.PYPI_TOKEN }}
 
-  build-cu128:
+  build-cu129:
     if: github.repository == 'sgl-project/sglang'
     needs: build-cu124
     runs-on: sgl-kernel-release-node
+    strategy:
+      matrix:
+        python-version: ['3.9']
+        cuda-version: ['12.9']
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: 'recursive'
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Build wheels
+        run: |
+          cd sgl-kernel
+          chmod +x ./build.sh
+          ./build.sh "${{ matrix.python-version }}" "${{ matrix.cuda-version }}"
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}
+          path: sgl-kernel/dist/*
+
+  release-cu129:
+    needs: build-cu129
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-*
+
+      - name: Set tag name
+        id: set_tag_name
+        run: |
+          if [ -z "${{ inputs.tag_name }}" ]; then
+            TAG_NAME="v$(cat sgl-kernel/python/sgl_kernel/version.py | cut -d'"' -f2)"
+            echo "tag_name=$TAG_NAME" >> $GITHUB_OUTPUT
+          else
+            echo "tag_name=${{ inputs.tag_name }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.set_tag_name.outputs.tag_name }}
+          repository: sgl-project/whl
+          token: ${{ secrets.WHL_TOKEN }}
+          files: |
+            sgl-kernel/dist/*
+
+      - name: Clone wheel index
+        run: git clone https://oauth2:${WHL_TOKEN}@github.com/sgl-project/whl.git sgl-whl
+        env:
+          WHL_TOKEN: ${{ secrets.WHL_TOKEN }}
+
+      - name: Update wheel index
+        run: python3 scripts/update_kernel_whl_index.py --cuda 129
+
+      - name: Push wheel index
+        run: |
+          cd sgl-whl
+          git config --local user.name "github-actions[bot]"
+          git config --local user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git add -A
+          git commit -m "update whl index"
+          git push
+
+  build-cu128:
+    if: github.repository == 'sgl-project/sglang'
+    needs: build-cu129
+    runs-on: sgl-kernel-release-node
     strategy:
       matrix:
         python-version: ['3.9']
@@ -76,7 +155,7 @@ jobs:
           name: wheel-python${{ matrix.python-version }}-cuda${{ matrix.cuda-version }}
           path: sgl-kernel/dist/*
 
-  release:
+  release-cu128:
     needs: build-cu128
     runs-on: ubuntu-latest
     steps:

sgl-kernel/build.sh

@@ -21,7 +21,10 @@ else
    BUILDER_NAME="pytorch/manylinux2_28-builder"
 fi
 
-if [ ${CUDA_VERSION} = "12.8" ]; then
+if [ ${CUDA_VERSION} = "12.9" ]; then
+   DOCKER_IMAGE="${BUILDER_NAME}:cuda${CUDA_VERSION}"
+   TORCH_INSTALL="pip install --no-cache-dir torch==2.8.0 --index-url https://download.pytorch.org/whl/test/cu129"
+elif [ ${CUDA_VERSION} = "12.8" ]; then
    DOCKER_IMAGE="${BUILDER_NAME}:cuda${CUDA_VERSION}"
    TORCH_INSTALL="pip install --no-cache-dir torch==2.8.0 --index-url https://download.pytorch.org/whl/test/cu128"
 else