Merge branch 'sgl-cmake2' of https://github.com/1329009851/sgl-kernel-npu into sgl-cmake2

* 'sgl-cmake2' of https://github.com/1329009851/sgl-kernel-npu:
  CI execution requirements for separating a2 and a3 (sgl-project#367)
  Fix the bug that total expert num greater than 256 or local expert num is less than 8 (sgl-project#364)
  adapt ant moving to A2 single machine (sgl-project#362)
  reset ci -- run test mixed running for experts on a2. (sgl-project#365)
  Revert "Build the deepep package with the chip model included. (sgl-project#274)" (sgl-project#363)
  fix:buffer control (sgl-project#361)
  Build the deepep package with the chip model included. (sgl-project#274)
  bugfix wrong packages build dir (sgl-project#360)
  bump version to 2026.02.01 (sgl-project#359)
  Cover the workflows cases on a3 (sgl-project#321)
  release follows naming convention (sgl-project#356)
  Modify notifydispatch to support DEEPEP_NORMAL_LONG_SEQ_ROUND up to 128. (sgl-project#352)
  fix the hanging bug (sgl-project#355)
  [Bugfix] Fix build script working with cann 8.5.0 (sgl-project#354)
  Modify the description of DeepEP in the README file. (sgl-project#348)
  Revert "Add scripts for building CMake files (sgl-project#344)" (sgl-project#353)
  Add scripts for building CMake files (sgl-project#344)
  Support x86_64 and aarch64 binary release (sgl-project#325)
  add function for deep-ep tests (sgl-project#301)
  [Doc] Improved README.md content and English grammar and integrated the DeepWiki badge for Ask AI (sgl-project#345)

Author: 1329009851

.github/workflows/build_and_release.yml

@@ -11,23 +11,30 @@ on:
     paths:
       - '.github/workflows/build_and_release.yml'
       - 'config.ini'
+      - 'build.sh'
 
 jobs:
 
   build-and-release:
-    strategy:
-      matrix:
-        os: [ubuntu-24.04-arm]
-        hardware: [910b, a3]
-        cann_version: [8.5.0]
-    runs-on: ${{ matrix.os }}
-    container:
-      image: quay.io/ascend/cann:${{ matrix.cann_version }}-${{ matrix.hardware }}-ubuntu22.04-py3.11
-    permissions:
-      contents: write
     defaults:
       run:
         shell: bash
+    permissions:
+      contents: write
+    strategy:
+      matrix:
+        arch: [x86_64, aarch64]
+        npu_hardware: [910b, a3]
+        cann_version: [8.3.rc2, 8.5.0]
+        # Ref: https://docs.github.com/en/actions/reference/runners/github-hosted-runners#standard-github-hosted-runners-for-public-repositories
+        include:
+          - arch: x86_64
+            runner: ubuntu-24.04
+          - arch: aarch64
+            runner: ubuntu-24.04-arm
+    runs-on: ${{ matrix.runner }}
+    container:
+      image: quay.io/ascend/cann:${{ matrix.cann_version }}-${{ matrix.npu_hardware }}-ubuntu22.04-py3.11
 
     steps:
       - name: Checkout repository
@@ -39,13 +46,11 @@ jobs:
 
       - name: Install dependency
         run: |
-          env
           bash scripts/npu_ci_install_dependency.sh
 
       - name: Build SGL-Kernel-NPU
         run: |
           env -i PATH=${PATH} bash --login -c "
-            env
             export LD_LIBRARY_PATH=${ASCEND_HOME_PATH}/runtime/lib64/stub:${LD_LIBRARY_PATH} && \
             ./build.sh -a kernels
           "
@@ -58,15 +63,15 @@ jobs:
           "
 
       - name: Build DeepEP for 910b
-        if: matrix.hardware == '910b'
+        if: matrix.npu_hardware == '910b'
         run: |
           env -i PATH=${PATH} bash --login -c "
             export LD_LIBRARY_PATH=${ASCEND_HOME_PATH}/runtime/lib64/stub:${LD_LIBRARY_PATH} && \
             ./build.sh -a deepep2
           "
 
       - name: Build DeepEP for a3
-        if: matrix.hardware == 'a3'
+        if: matrix.npu_hardware == 'a3'
         run: |
           env -i PATH=${PATH} bash --login -c "
             export LD_LIBRARY_PATH=${ASCEND_HOME_PATH}/runtime/lib64/stub:${LD_LIBRARY_PATH} && \
@@ -75,12 +80,18 @@ jobs:
 
       - name: Pack up packages
         run: |
-          zip -v "sgl-kernel-npu_${{ github.event.release.tag_name }}_${{ matrix.cann_version }}_${{ matrix.hardware }}.zip" output/*.whl
+          export TORCH_DEVICE_BACKEND_AUTOLOAD=0
+          TORCH_VERSION=$(python3 -c "import torch; print(torch.__version__)" | awk -F'+' '{print $1}')
+          PYTHON_VERSION=$(python3 -c "import platform; print(platform.python_version())" | awk -F'.' '{print $1$2}')
+          PACKAGE_NAME="sgl-kernel-npu-${{ github.event.release.tag_name }}-torch${TORCH_VERSION}-py${PYTHON_VERSION}-cann${{ matrix.cann_version }}-${{ matrix.npu_hardware }}-${{ matrix.arch }}.zip"
+          cd output/
+          zip -v ${PACKAGE_NAME} ./*.whl
+          ls -al
 
       - name: Upload Release Artifacts
         if: github.event_name != 'pull_request'
         uses: softprops/action-gh-release@v2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
-          files: ./*.zip
+          files: ./output/*.zip