Created new changes in the functions

.github/actions/llm/download-llm-binary/action.yml

@@ -27,6 +27,7 @@ runs:
           mv windows-avx2/* python/llm/llm-binary/
           mv windows-avx-vnni/* python/llm/llm-binary/
           mv windows-avx/* python/llm/llm-binary/
+          mv windows-npu-level0/* python/llm/llm-binary/
         fi
         rm -rf linux-avx2 || true
         rm -rf linux-avx512 || true
@@ -36,3 +37,4 @@ runs:
         rm -rf windows-avx2 || true
         rm -rf windows-avx-vnni || true
         rm -rf windows-avx || true
+        rm -rf windows-npu-level0 || true

.github/actions/llm/setup-llm-env/action.yml

@@ -29,6 +29,9 @@ runs:
         sed -i 's/"bigdl-core-xe-addons-21==" + CORE_XE_VERSION/"bigdl-core-xe-addons-21"/g' python/llm/setup.py
         sed -i 's/"bigdl-core-xe-esimd-21==" + CORE_XE_VERSION/"bigdl-core-xe-esimd-21"/g' python/llm/setup.py
 
+        pip uninstall bigdl-core-xe-all -y || true
+        sed -i 's/"bigdl-core-xe-all==" + CORE_XE_VERSION/"bigdl-core-xe-all"/g' python/llm/setup.py
+
         pip install requests
         if [[ ${{ runner.os }} == 'Linux' ]]; then
           bash python/llm/dev/release_default_linux.sh default false
@@ -45,6 +48,9 @@ runs:
         elif [[ ${{ inputs.extra-dependency }} == 'xpu_2.1' ]]; then
           pip install --upgrade --pre -i https://pypi.python.org/simple --force-reinstall "python/llm/dist/${whl_name}[xpu_2.1]" --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/ 
           pip install pytest expecttest
+        elif [[ ${{ inputs.extra-dependency }} == 'xpu_2.6' ]]; then
+          pip install --upgrade --pre -i https://pypi.python.org/simple --force-reinstall "python/llm/dist/${whl_name}[xpu_2.6]" --extra-index-url https://download.pytorch.org/whl/test/xpu
+          pip install pytest
         else
           if [[ ${{ runner.os }} == 'Linux' ]]; then
             pip install --upgrade --pre -i https://pypi.python.org/simple --force-reinstall "python/llm/dist/${whl_name}[all]" --extra-index-url https://download.pytorch.org/whl/cpu

.github/workflows/llm-binary-build.yml

@@ -443,6 +443,64 @@ jobs:
           path: |
             release
 
+  check-windows-npu-level0-artifact:
+    if: ${{contains(inputs.platform, 'Windows')}}
+    runs-on: [Shire]
+    outputs:
+      if-exists: ${{steps.check_artifact.outputs.exists}}
+    steps:
+      - name: Check if built
+        id: check_artifact
+        uses: xSAVIKx/artifact-exists-action@v0
+        with:
+          name: windows-npu-level0
+
+  windows-build-npu-level0:
+    runs-on: [self-hosted, Windows, npu-level0]
+    needs: check-windows-npu-level0-artifact
+    if: needs.check-windows-npu-level0-artifact.outputs.if-exists == 'false'
+    steps:
+      - name: Set access token
+        run: |
+          echo "github_access_token=$env:GITHUB_ACCESS_TOKEN" >> $env:GITHUB_ENV
+          echo "github_access_token=$env:GITHUB_ACCESS_TOKEN"
+      - uses: actions/checkout@f43a0e5ff2bd294095638e18286ca9a3d1956744 # actions/checkout@v3
+        with:
+          repository: "intel-analytics/llm.cpp"
+          ref: ${{ inputs.llmcpp-ref }}
+          token: ${{ env.github_access_token }}
+          submodules: "recursive"
+      - name: Add msbuild to PATH
+        uses: microsoft/[email protected]
+        with:
+          msbuild-architecture: x64
+      - name: Add cmake to PATH
+        uses: ilammy/msvc-dev-cmd@v1
+      - name: Build binary
+        shell: cmd
+        run: |
+          call "C:\Program Files (x86)\Intel\openvino_2024.4.0\setupvars.bat"
+          cd bigdl-core-npu-level0
+          sed -i "/FetchContent_MakeAvailable(intel_npu_acceleration_library)/s/^/#/" CMakeLists.txt
+          mkdir build
+          cd build
+          cmake ..
+          cmake --build . --config Release -t pipeline
+      - name: Move release binary
+        shell: powershell
+        run: |
+          cd bigdl-core-npu-level0
+          if (Test-Path ./release) { rm -r -fo release }
+          mkdir release
+          mv build/Release/pipeline.dll release/pipeline.dll
+      - name: Archive build files
+        uses: actions/upload-artifact@v3
+        with:
+          name: windows-npu-level0
+          path: |
+            bigdl-core-npu-level0/release
+
+
   # to make llm-binary-build optionally skippable
   dummy-step:
     if: ${{ inputs.platform == 'Dummy' }}

.github/workflows/llm-c-evaluation.yml

@@ -10,12 +10,12 @@ permissions:
 
 # Controls when the action will run.
 on:
-  schedule:
-    - cron: "00 15 * * *" # GMT time, 15:00 GMT == 23:00 Beijing Time
-  pull_request:
-    branches: [main]
-    paths:
-      - ".github/workflows/llm-c-evaluation.yml"
+  # schedule:
+  #   - cron: "00 15 * * *" # GMT time, 15:00 GMT == 23:00 Beijing Time
+  # pull_request:
+  #   branches: [main]
+  #   paths:
+  #     - ".github/workflows/llm-c-evaluation.yml"
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:
     inputs:
@@ -204,7 +204,7 @@ jobs:
           pip install pandas==1.5.3
 
       - name: Download ceval results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: ceval_results
           path: results
@@ -259,7 +259,7 @@ jobs:
           fi
 
       - name: Download ceval results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: results_${{ needs.set-matrix.outputs.date }}
           path:  ${{ env.ACC_FOLDER }}

.github/workflows/llm-harness-evaluation.yml

@@ -10,12 +10,12 @@ permissions:
 
 # Controls when the action will run.
 on:
-  schedule:
-    - cron: "30 12 * * *" # GMT time, 12:30 GMT == 20:30 China
-  pull_request:
-    branches: [main]
-    paths:
-      - ".github/workflows/llm-harness-evaluation.yml"
+  # schedule:
+  #   - cron: "30 12 * * *" # GMT time, 12:30 GMT == 20:30 China
+  # pull_request:
+  #   branches: [main]
+  #   paths:
+  #     - ".github/workflows/llm-harness-evaluation.yml"
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:
     inputs:
@@ -220,7 +220,7 @@ jobs:
           pip install --upgrade pip
           pip install jsonlines  pytablewriter regex
       - name: Download all results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: harness_results
           path: results        
@@ -260,7 +260,7 @@ jobs:
           fi
 
       - name: Download harness results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: harness_results
           path: ${{ env.ACC_FOLDER}}/${{ env.DATE }}

.github/workflows/llm-nightly-test.yml

@@ -86,7 +86,6 @@ jobs:
         shell: bash
         run: |
           python -m pip install --upgrade pip
-          python -m pip install --upgrade setuptools==58.0.4
           python -m pip install --upgrade wheel
 
       - name: Download llm binary

.github/workflows/llm-ppl-evaluation.yml

@@ -10,12 +10,12 @@ permissions:
 
 # Controls when the action will run.
 on:
-  schedule:
-    - cron: "00 12 * * *" # GMT time, 12:00 GMT == 20:00 China
-  pull_request:
-    branches: [main]
-    paths:
-      - ".github/workflows/llm-ppl-evaluation.yml"
+  # schedule:
+  #   - cron: "00 12 * * *" # GMT time, 12:00 GMT == 20:00 China
+  # pull_request:
+  #   branches: [main]
+  #   paths:
+  #     - ".github/workflows/llm-ppl-evaluation.yml"
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:
     inputs:
@@ -206,7 +206,7 @@ jobs:
           pip install --upgrade pip
           pip install jsonlines  pytablewriter regex
       - name: Download all results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: ppl_results
           path: results        
@@ -245,7 +245,7 @@ jobs:
           fi
 
       - name: Download ppl results
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: ppl_results
           path: ${{ env.ACC_FOLDER}}/${{ env.DATE }}

.github/workflows/llm-whisper-evaluation.yml

@@ -10,12 +10,12 @@ permissions:
 
 # Controls when the action will run.
 on:
-  schedule:
-    - cron: "00 13 * * *" # GMT time, 13:00 GMT == 21:00 China
-  pull_request:
-    branches: [main]
-    paths:
-      - ".github/workflows/llm-whisper-evaluation.yml"
+  # schedule:
+  #   - cron: "00 13 * * *" # GMT time, 13:00 GMT == 21:00 China
+  # pull_request:
+  #   branches: [main]
+  #   paths:
+  #     - ".github/workflows/llm-whisper-evaluation.yml"
   # Allows you to run this workflow manually from the Actions tab
   workflow_dispatch:
     inputs:
@@ -176,14 +176,14 @@ jobs:
 
       - name: Download all results for nightly run
         if: github.event_name == 'schedule'
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: whisper_results
           path: ${{ env.NIGHTLY_FOLDER}}/${{ env.OUTPUT_PATH }}
 
       - name: Download all results for pr run
         if: github.event_name == 'pull_request'
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@4.1.7
         with:
           name: whisper_results
           path: ${{ env.PR_FOLDER}}/${{ env.OUTPUT_PATH }}

.github/workflows/llm_example_tests.yml

@@ -61,7 +61,6 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install --upgrade setuptools==58.0.4
           python -m pip install --upgrade wheel
 
       - name: Download llm binary