[NPU] Diffusion CI Ground Truth Generation (NPU) (#24630)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Elizaveta Martirosian <you@example.com>
Co-authored-by: Elizaveta Martirosian <elizaveta.martirosian@gmail.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>

.github/workflows/pr-test-npu.yml

@@ -341,7 +341,7 @@ jobs:
           SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
         run: |
           cd python
-          python3 sglang/multimodal_gen/test/run_suite_npu.py --suite 1-npu
+          python3 sglang/multimodal_gen/test/run_suite.py --suite 1-npu
 
       - name: Upload diffusion failure artifacts
         if: always()
@@ -398,7 +398,7 @@ jobs:
           SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
         run: |
           cd python
-          python3 sglang/multimodal_gen/test/run_suite_npu.py --suite 2-npu
+          python3 sglang/multimodal_gen/test/run_suite.py --suite 2-npu
 
       - name: Upload diffusion failure artifacts
         if: always()
@@ -409,63 +409,6 @@ jobs:
           if-no-files-found: ignore
           retention-days: 7
 
-  multimodal-gen-test-8-npu-a3:
-    needs: [check-changes, pr-gate, set-image-config]
-    if: needs.check-changes.outputs.multimodal_gen == 'true'
-    runs-on: linux-aarch64-a3-8
-    container:
-      image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Mark repository safe
-        run: |
-          git config --system --add safe.directory ${GITHUB_WORKSPACE}
-
-      - name: Install dependencies
-        env:
-          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
-          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
-          UV_INDEX_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
-          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
-          RUSTUP_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local:8082"
-        run: |
-          # speed up by using infra cache services
-          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
-          sed -Ei "s@(ports|archive).ubuntu.com@${CACHING_URL}:8081@g" /etc/apt/sources.list
-          pip config set global.index-url http://${CACHING_URL}/pypi/simple
-          pip config set global.trusted-host "${CACHING_URL}"
-
-          bash scripts/ci/npu/npu_ci_install_dependency.sh a3
-          # copy required file from our daily cache
-          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
-          # copy gsm8k dataset
-          cp ~/.cache/modelscope/hub/datasets/tmp/test.jsonl /tmp
-
-      - name: Run test
-        timeout-minutes: 60
-        env:
-          SGLANG_USE_MODELSCOPE: true
-          SGLANG_IS_IN_CI: true
-          HF_ENDPOINT: https://hf-mirror.com
-          TORCH_EXTENSIONS_DIR: /tmp/torch_extensions
-          PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
-          STREAMS_PER_DEVICE: 32
-          SGLANG_DIFFUSION_ARTIFACT_DIR: ${{ github.workspace }}/diffusion-failures
-        run: |
-          cd python
-          python3 sglang/multimodal_gen/test/run_suite_npu.py --suite 8-npu
-
-      - name: Upload diffusion failure artifacts
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: diffusion-failures-npu-8-${{ github.run_attempt }}
-          path: diffusion-failures/
-          if-no-files-found: ignore
-          retention-days: 7
-
   pr-test-npu-finish:
     needs:
       [
@@ -478,7 +421,6 @@ jobs:
 
         multimodal-gen-test-1-npu-a3,
         multimodal-gen-test-2-npu-a3,
-        multimodal-gen-test-8-npu-a3,
       ]
     if: always()
     runs-on: ubuntu-latest