From 724b2ae66d9e7d04dd8076736631ea0b286eb796 Mon Sep 17 00:00:00 2001
From: Shaojun Liu <61072813+liu-shaojun@users.noreply.github.com>
Date: Fri, 11 Oct 2024 16:05:20 +0800
Subject: [PATCH] add npu-level0 pipeline.dll to ipex-llm (#12181)

* add npu-level0 pipeline.dll to ipex-llm

* test

* update runner label

* fix

* update

* fix

* fix
---
 .../llm/download-llm-binary/action.yml        |  2 +
 .github/workflows/llm-binary-build.yml        | 56 +++++++++++++++++++
 python/llm/setup.py                           |  3 +-
 3 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/.github/actions/llm/download-llm-binary/action.yml b/.github/actions/llm/download-llm-binary/action.yml
index c15bfe49..8726969c 100644
--- a/.github/actions/llm/download-llm-binary/action.yml
+++ b/.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
diff --git a/.github/workflows/llm-binary-build.yml b/.github/workflows/llm-binary-build.yml
index 26f061b3..211a8aa3 100644
--- a/.github/workflows/llm-binary-build.yml
+++ b/.github/workflows/llm-binary-build.yml
@@ -443,6 +443,62 @@ 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/setup-msbuild@v1.1
+        with:
+          msbuild-architecture: x64
+      - name: Add cmake to PATH
+        uses: ilammy/msvc-dev-cmd@v1
+      - name: Build binary
+        shell: powershell
+        run: |
+          cd bigdl-core-npu-level0
+          mkdir build
+          cd build
+          cmake ..
+          cmake --build . --config Release -j
+      - 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' }}
diff --git a/python/llm/setup.py b/python/llm/setup.py
index 5556f3d0..7169d75f 100644
--- a/python/llm/setup.py
+++ b/python/llm/setup.py
@@ -85,7 +85,8 @@ windows_binarys = [
     "quantize-llama_vnni.exe",
     "quantize-gptneox_vnni.exe",
     "quantize-bloom_vnni.exe",
-    "quantize-starcoder_vnni.exe"
+    "quantize-starcoder_vnni.exe",
+    "pipeline.dll"
 ]
 linux_binarys = [
     "libllama_avx.so",