[test] add npu test yaml and add ascend a3 docker file (#9547)

Co-authored-by: jiaqiw09 <jiaqiw960714@gmail.com>

.github/workflows/docker.yml

@@ -27,14 +27,18 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        device:
-          - "cuda"
-          - "npu"
+        include:
+          - device: "cuda"
+            npu_type: ""
+          - device: "npu"
+            npu_type: "a2"
+          - device: "npu"
+            npu_type: "a3"
 
     runs-on: ubuntu-latest
 
     concurrency:
-      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.device }}
+      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.device }}-${{ matrix.npu_type }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 
     environment:
@@ -76,7 +80,7 @@ jobs:
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Login to Quay
-        if: ${{ github.event_name != 'pull_request' && matrix.device == 'npu' }}
+        if: ${{ github.event_name != 'pull_request' && matrix.device == 'npu'}}
         uses: docker/login-action@v3
         with:
           registry: quay.io
@@ -97,8 +101,8 @@ jobs:
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
-      - name: Build and push Docker image (NPU)
-        if: ${{ matrix.device == 'npu' }}
+      - name: Build and push Docker image (NPU-A2)
+        if: ${{ matrix.device == 'npu' && matrix.npu_type == 'a2' }}
         uses: docker/build-push-action@v6
         with:
           context: .
@@ -110,3 +114,19 @@ jobs:
             quay.io/ascend/llamafactory:${{ steps.version.outputs.tag }}-npu-a2
           cache-from: type=gha
           cache-to: type=gha,mode=max
+
+      - name: Build and push Docker image (NPU-A3)
+        if: ${{ matrix.device == 'npu' && matrix.npu_type == 'a3' }}
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          file: ./docker/docker-npu/Dockerfile
+          build-args: |
+            BASE_IMAGE=quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+            docker.io/hiyouga/llamafactory:${{ steps.version.outputs.tag }}-npu-a3
+            quay.io/ascend/llamafactory:${{ steps.version.outputs.tag }}-npu-a3
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/tests_npu.yml

@@ -0,0 +1,87 @@
+name: tests_npu
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - "main"
+    paths:
+      - "**/*.py"
+      - "requirements.txt"
+      - "Makefile"
+      - ".github/workflows/*.yml"
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - "**/*.py"
+      - "requirements.txt"
+      - "Makefile"
+      - ".github/workflows/*.yml"
+
+jobs:
+  tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        python:
+          - "3.11"
+        os:
+          - "linux-aarch64-a2-4"
+        pytorch_npu:
+          - "2.7.1"
+
+    runs-on: ${{ matrix.os }}
+
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}-${{ matrix.os }}-${{ matrix.python }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+    container:
+      image: ascendai/cann:8.3.rc2-910b-ubuntu22.04-py3.11
+      env:
+        HF_ENDPOINT: https://hf-mirror.com
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        OS_NAME: ${{ matrix.os }}
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install ".[torch-npu,dev]" torch-npu==${{matrix.pytorch_npu}}
+
+      - name: Install node
+        run: |
+          apt-get update || true
+          apt-get install -y curl
+          curl -fsSL https://deb.nodesource.com/setup_20.x | bash -
+          apt-get install -y nodejs
+
+      - name: Cache files
+        id: hf-hub-cache
+        uses: actions/cache@v4
+        with:
+          path: ${{ runner.temp }}/huggingface
+          key: huggingface-${{ matrix.os }}-${{ matrix.python }}-${{ hashFiles('tests/version.txt') }}
+
+      - name: Check quality
+        run: |
+          make style && make quality
+
+      - name: Check license
+        run: |
+          make license
+
+      - name: Check build
+        run: |
+          make build
+
+      - name: Test with pytest
+        run: |
+          make test
+        env:
+          HF_HOME: /root/.cache/huggingface
+          HF_HUB_OFFLINE: "${{ steps.hf-hub-cache.outputs.cache-hit == 'true' && '1' || '0' }}"