feat: sync npu nightly test improvements from Ascend testcases (#29403)

.github/workflows/nightly-test-npu-e2e-single-node.yml

@@ -30,6 +30,16 @@ on:
         type: boolean
         default: false
         description: use sglang from source code or from docker image
+      install_sglang_deps:
+        required: false
+        type: boolean
+        default: false
+        description: install sglang dependencies (e.g. PyTorch, CANN packages) when using source installation
+      device_type_for_deps:
+        required: false
+        type: string
+        default: 'a3'
+        description: device type for dependency installation (a3 or 910b)
       transformers_version:
         required: false
         type: string
@@ -54,8 +64,25 @@ jobs:
         run: |
           npu-smi info
 
+      - name: Install sglang dependencies
+        if: ${{ inputs.install_sglang_deps == true }}
+        shell: bash
+        env:
+          TORCH_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/whl/cpu"
+          PYPI_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          UV_INDEX_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple"
+          GITHUB_PROXY_URL: "https://gh-proxy.test.osinfra.cn/"
+          RUSTUP_CACHE_URL: "http://cache-service.nginx-pypi-cache.svc.cluster.local:8082"
+        run: |
+          CACHING_URL="cache-service.nginx-pypi-cache.svc.cluster.local"
+          sed -Ei "s@(ports|archive).ubuntu.com@${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 ${{ inputs.device_type_for_deps }}
+          cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
+
       - name: Run test
-        timeout-minutes: 120
+        timeout-minutes: 300
         env:
           SGLANG_USE_MODELSCOPE: true
           HF_ENDPOINT: https://hf-mirror.com

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

@@ -1,4 +1,4 @@
-name: Nightly Test (NPU)
+name: Nightly Test (NPU)
 on:
   schedule:
     - cron: '0 18 * * *'  # Execute at 2:00 a.m. Beijing Time every day
@@ -168,9 +168,9 @@ jobs:
             runner: linux-aarch64-a3-4
             test_case: test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_2p_in16k_out1k_50ms.py
             test_type: 'perf'
-          - name: qwen3_6_27b_w8a8_2p_in64k_out1k_50ms
+          - name: qwen3_6_27b_w8a8_1p_in64k_out1k_50ms
             runner: linux-aarch64-a3-4
-            test_case: test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_2p_in64k_out1k_50ms.py
+            test_case: test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py
             test_type: 'perf'
           - name: qwen3_6_27b_w8a8_2p_in128k_out1k_50ms
             runner: linux-aarch64-a3-4

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

@@ -408,6 +408,32 @@ jobs:
           if-no-files-found: ignore
           retention-days: 7
 
+  pr-single-node-tests:
+    name: single-node-poc
+    needs: [check-changes, pr-gate, set-image-config]
+    if: needs.check-changes.outputs.main_package == 'true'
+    strategy:
+      fail-fast: false
+      max-parallel: 6
+      matrix:
+        test_config:
+          # qwen3_6_27b performance tests
+          - name: qwen3_6_27b_w8a8_1p_in64k_out1k_50ms
+            runner: linux-aarch64-a3-2
+            test_case: test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py
+            test_type: 'perf'
+    uses: ./.github/workflows/nightly-test-npu-e2e-single-node.yml
+    with:
+      runner: ${{ matrix.test_config.runner }}
+      test_type: ${{ matrix.test_config.test_type }}
+      test_config_name: ${{ matrix.test_config.name }}
+      test_case: ${{ matrix.test_config.test_case }}
+      image: ${{ needs.set-image-config.outputs.CANN_image_a3 }}
+      install_sglang_from_source: false
+      install_sglang_deps: true
+      device_type_for_deps: 'a3'
+      transformers_version: ''
+
   pr-test-npu-finish:
     needs:
       [
@@ -420,6 +446,8 @@ jobs:
 
         multimodal-gen-test-1-npu-a3,
         multimodal-gen-test-2-npu-a3,
+
+        pr-single-node-tests,
       ]
     if: always()
     runs-on: ubuntu-latest