vllm-ascend 0.10.0rc1__tar.gz → 0.10.2rc1__tar.gz

vllm_ascend-0.10.2rc1/.gemini/config.yaml

@@ -0,0 +1,6 @@
+# https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github
+have_fun: false  # Just review the code
+code_review:
+  comment_severity_threshold: HIGH  # Reduce quantity of comments
+  pull_request_opened:
+    summary: false  # Don't summarize the PR in a separate comment

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/ISSUE_TEMPLATE/750-RFC.yml

@@ -40,7 +40,7 @@ body:
   attributes:
     label: Any Other Things.
     description: >
-      Any other things you would like to mention.
+      Any other things you would like to mention, such as feature branch request.
   validations:
     required: false
 - type: markdown

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/ISSUE_TEMPLATE/900-release-checklist.yml

@@ -30,6 +30,8 @@ body:
 
         - [ ] Add release note to docs/source/user_guide/release_notes.md
 
+        - [ ] Update release version in README.md and README.zh.md
+
         - [ ] Update version info in docs/source/community/versioning_policy.md
 
         - [ ] Update contributor info in docs/source/community/contributors.md

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/actionlint.yaml

@@ -11,3 +11,10 @@ self-hosted-runner:
     - linux-aarch64-310p-2
     - linux-aarch64-310p-4
     - ubuntu-24.04-arm
+    - linux-aarch64-a3-1
+    - linux-aarch64-a3-2
+    - linux-aarch64-a3-4
+    - linux-aarch64-a3-8
+    - linux-amd64-cpu-0
+    - linux-amd64-cpu-8
+    - linux-amd64-cpu-16

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/accuracy_test.yaml

@@ -70,6 +70,8 @@ jobs:
             runner: linux-aarch64-a2-1
           - model_name: Qwen3-30B-A3B
             runner: linux-aarch64-a2-2
+          - model_name: DeepSeek-V2-Lite
+            runner: linux-aarch64-a2-2
       fail-fast: false
 
     name: ${{ matrix.model_name }} accuracy
@@ -110,7 +112,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
-          ref: v0.10.0
+          ref: v0.10.2
           path: ./vllm-empty
 
       - name: Install vllm-project/vllm from source
@@ -200,9 +202,8 @@ jobs:
           markdown_name="${model_base_name}"
           echo "markdown_name=$markdown_name" >> $GITHUB_OUTPUT
           mkdir -p ./benchmarks/accuracy
-          pytest -sv ./tests/e2e/singlecard/models/test_lm_eval_correctness.py \
-          --config ./tests/e2e/singlecard/models/configs/${{ matrix.model_name }}.yaml \
-          --report_output ./benchmarks/accuracy/${model_base_name}.md 
+          pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py \
+          --config ./tests/e2e/models/configs/${{ matrix.model_name }}.yaml
 
       - name: Generate step summary
         if: ${{ always() }}
@@ -225,14 +226,14 @@ jobs:
 
     outputs:
       model_name: ${{ steps.set_output.outputs.model_name }}
-      
+      vllm_ascend_version: ${{ env.GHA_VLLM_ASCEND_VERSION }} 
+
   create_pr:
     runs-on: ubuntu-latest
     needs: accuracy_tests
     if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}
     env:
       UPSTREAM_REPO: vllm-project/vllm-ascend
-
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -257,10 +258,10 @@ jobs:
           TIMESTAMP=$(date +%Y%m%d%H%M%S)
           BRANCH_NAME="auto-pr/accuracy-report-${TIMESTAMP}"
           echo "BRANCH_NAME=${BRANCH_NAME}" >> $GITHUB_ENV
-          git checkout -B "${BRANCH_NAME}" upstream/${{ github.event.inputs.vllm-ascend-version }}
+          git checkout -B "${BRANCH_NAME}" upstream/main
 
       - name: Download only current run reports
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v5
         with:
           path: ./docs/source/developer_guide/evaluation/accuracy_report
           pattern: report-*
@@ -298,11 +299,11 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN }}
         run: |
           git add ./docs/source/developer_guide/evaluation/accuracy_report/*.md
-          git commit -s -m "[Doc] Update accuracy reports for ${{ github.event.inputs.vllm-ascend-version }}"
+          git commit -s -m "[Doc] Update accuracy reports for ${{ needs.accuracy_tests.outputs.vllm_ascend_version }}"
           git push -f origin "${{ env.BRANCH_NAME }}"
 
       - name: Create PR in upstream via API
-        uses: actions/github-script@v7
+        uses: actions/github-script@v8
         with:
           github-token: ${{ secrets.PAT_TOKEN }}
           script: |
@@ -310,9 +311,9 @@ jobs:
               owner: 'vllm-project',
               repo: 'vllm-ascend',
               head: `vllm-ascend-ci:${{ env.BRANCH_NAME }}`,
-              base: '${{ github.event.inputs.vllm-ascend-version }}',
-              title: `[Doc] Update accuracy reports for ${{ github.event.inputs.vllm-ascend-version }}`,
-              body: `The accuracy results running on NPU Altlas A2 have changed, updating reports for: All models (Qwen/Qwen3-30B-A3B, Qwen2.5-VL-7B-Instruct, Qwen3-8B-Base)
+              base: 'main',
+              title: `[Doc] Update accuracy reports for ${{ needs.accuracy_tests.outputs.vllm_ascend_version }}`,
+              body: `The accuracy results running on NPU Altlas A2 have changed, updating reports for: All models (Qwen3-30B-A3B, Qwen2.5-VL-7B-Instruct, Qwen3-8B-Base, DeepSeek-V2-Lite)
             
               - [Workflow run][1]
               

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/format_pr_body.yaml

@@ -46,7 +46,7 @@ jobs:
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
       - name: Set up Python
         uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_310p_openeuler.yml

@@ -25,6 +25,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -43,17 +44,28 @@ on:
       - 'CMakeLists.txt'
       - 'csrc/**'
 
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: >-
       ${{
           github.event_name == 'push' && github.repository_owner == 'vllm-project' &&
           'ubuntu-latest' ||
           'ubuntu-24.04-arm'
       }}
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_310p_ubuntu.yml

@@ -25,6 +25,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -42,14 +43,25 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
 
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: ubuntu-latest
-
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_a3_openeuler.yml

@@ -25,6 +25,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -43,17 +44,28 @@ on:
       - 'CMakeLists.txt'
       - 'csrc/**'
 
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: >-
       ${{
           github.event_name == 'push' && github.repository_owner == 'vllm-project' &&
           'ubuntu-latest' ||
           'ubuntu-24.04-arm'
       }}
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_a3_ubuntu.yml

@@ -25,6 +25,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -42,14 +43,25 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
 
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: ubuntu-latest
-
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_openeuler.yml

@@ -24,6 +24,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -42,17 +43,28 @@ on:
       - 'CMakeLists.txt'
       - 'csrc/**'
 
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: >-
       ${{
           github.event_name == 'push' && github.repository_owner == 'vllm-project' &&
           'ubuntu-latest' ||
           'ubuntu-24.04-arm'
       }}
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/image_ubuntu.yml

@@ -25,6 +25,7 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+    types: [ labeled ]
   push:
     # Publish image when tagging, the Dockerfile in tag will be build as tag image
     branches:
@@ -42,14 +43,25 @@ on:
       - 'cmake/**'
       - 'CMakeLists.txt'
       - 'csrc/**'
+
+# only cancel in-progress runs of the same workflow
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
 
   build:
     name: vllm-ascend image build
+    # Only arm64 build on openEuler arm64, only amd64 build on Ubuntu amd64
+    # Push event or PR with both 'ready' and 'ready-for-test' labels
     runs-on: ubuntu-latest
-
+    if: ${{ github.event_name == 'push' || (contains(github.event.pull_request.labels.*.name, 'ready') && contains(github.event.pull_request.labels.*.name, 'ready-for-test')) }}
     steps:
     - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        persist-credentials: false
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/nightly_benchmarks.yaml

@@ -51,7 +51,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: v0.10.0
+          - vllm_branch: v0.10.2
             vllm_ascend_branch: main
             vllm_use_v1: 1
       max-parallel: 1

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/pre-commit.yml

@@ -35,3 +35,4 @@ jobs:
         SHELLCHECK_OPTS: "--exclude=SC2046,SC2006,SC2086" # Exclude SC2046, SC2006, SC2086 for actionlint
       with:
         extra_args: --all-files --hook-stage manual
+

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/release_code.yml

@@ -43,7 +43,7 @@ jobs:
       matrix:
         python-version: ["3.11"]
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
       - name: Print
         run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/release_whl.yml

@@ -52,7 +52,7 @@ jobs:
          ) }}
     runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+    - uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
     - name: Print
       run: |

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/reminder_comment.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Remind to run full CI on PR
-        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
         with:
           script: |
             github.rest.issues.createComment({

vllm_ascend-0.10.0rc1/.github/workflows/vllm_ascend_test_long_term.yaml → vllm_ascend-0.10.2rc1/.github/workflows/vllm_ascend_dist.yaml

@@ -1,6 +1,5 @@
 #
 # Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
-# This file is a part of the vllm-ascend project.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -13,13 +12,14 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+# This file is a part of the vllm-ascend project.
 #
-name: 'e2e test / long-term-test'
+
+name: 'e2e test / a3-test'
 
 on:
-  schedule:
-    # Runs at 23:00 UTC (7:00 AM Beijing) every day
-    - cron: '0 23 * * *'
+  workflow_call:
+
   pull_request:
     types: [ labeled ]
 
@@ -31,26 +31,25 @@ defaults:
     shell: bash -el {0}
 
 # only cancel in-progress runs of the same workflow
+# and ignore the lint / 8 cards test type
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
 jobs:
-  long-term-test:
-    # long-term-test will be triggered when tag 'long-term-test' & 'ready-for-test' or schedule job
-    if: ${{ contains(github.event.pull_request.labels.*.name, 'long-term-test')  && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'schedule' }}
+  e2e:
+    # only trigger e2e test after lint passed and the change is e2e related with pull request.
+    if: ${{ contains(github.event.pull_request.labels.*.name, 'dist-test') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'workflow_dispatch' }}
     strategy:
-      max-parallel: 2
       matrix:
-        os: [linux-aarch64-a2-1, linux-aarch64-a2-2]
-        vllm_version: [main, v0.10.0]
-    name: vLLM Ascend long term test
+        os: [linux-aarch64-a3-8]
+        vllm_version: [v0.10.2]
+    name: vLLM Ascend test
     runs-on: ${{ matrix.os }}
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
+      image: m.daocloud.io/quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11
       env:
-        VLLM_LOGGING_LEVEL: ERROR
-        VLLM_USE_MODELSCOPE: True
+        DEBIAN_FRONTEND: noninteractive
     steps:
       - name: Check npu and CANN info
         run: |
@@ -59,11 +58,11 @@ jobs:
 
       - name: Config mirrors
         run: |
-          sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
-          pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
-          pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
+          sed -i 's|ports.ubuntu.com|mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list
+          pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
           apt-get update -y
           apt install git -y
+          git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
 
       - name: Checkout vllm-project/vllm-ascend repo
         uses: actions/checkout@v4
@@ -86,17 +85,16 @@ jobs:
           VLLM_TARGET_DEVICE=empty pip install -e .
 
       - name: Install vllm-project/vllm-ascend
-        env:
-          PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
         run: |
+          export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
+          export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
           pip install -r requirements-dev.txt
           pip install -v -e .
 
-      - name: Run vllm-project/vllm-ascend long term test
+      - name: Run vllm-project/vllm-ascend test for V1 Engine
+        env:
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+          VLLM_USE_MODELSCOPE: True
         run: |
-          if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
-            pytest -sv tests/e2e/long_term/accuracy/accuracy_singlecard.py
-          else
-            # accuracy test multi card
-            pytest -sv tests/e2e/long_term/accuracy/accuracy_multicard.py
-          fi
+          # TODO: enable more tests
+          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/vllm_ascend_test.yaml

@@ -25,7 +25,6 @@ on:
     branches:
       - 'main'
       - '*-dev'
-
 # Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly
 # declared as "shell: bash -el {0}" on steps that need to be properly activated.
 # It's used to activate ascend-toolkit environment variables.
@@ -44,6 +43,7 @@ jobs:
     uses: ./.github/workflows/pre-commit.yml
 
   changes:
+    if: github.event_name == 'pull_request'
     runs-on: ubuntu-latest
     outputs:
       e2e_tracker: ${{ steps.filter.outputs.e2e_tracker }}
@@ -68,6 +68,7 @@ jobs:
               - 'packages.txt'
             ut_tracker:
               - 'tests/ut/**'
+
   ut:
     needs: [lint, changes]
     name: unit test
@@ -81,7 +82,7 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [main, v0.10.0]
+        vllm_version: [v0.10.2]
     steps:
       - name: Install packages
         run: |
@@ -117,7 +118,7 @@ jobs:
           TORCH_DEVICE_BACKEND_AUTOLOAD: 0
         run: |
           export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/x86_64-linux/devlib
-          pytest -sv --cov --cov-report=xml:unittests-coverage.xml tests/ut
+          pytest -sv --cov --cov-report=xml:unittests-coverage.xml tests/ut --ignore=tests/ut/test_platform.py --ignore=tests/ut/ops/test_vocab_parallel_embedding.py
 
       - name: Upload coverage to Codecov
         if: ${{ matrix.vllm_version == 'main' }}
@@ -129,16 +130,16 @@ jobs:
           name: vllm-ascend
           verbose: true
 
-  e2e:
+  e2e-light:
     needs: [lint, changes]
     # only trigger e2e test after lint passed and the change is e2e related with pull request.
-    if: ${{ github.event_name == 'pull_request' && needs.lint.result == 'success' && needs.changes.outputs.e2e_tracker == 'true' }}
+    if: ${{ github.event_name == 'pull_request' && needs.lint.result == 'success' && needs.changes.outputs.e2e_tracker == 'true' && !contains(github.event.pull_request.labels.*.name, 'ready') }}
     strategy:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-1]
-        vllm_version: [main, v0.10.0]
-    name: singlecard e2e test
+        vllm_version: [v0.10.2]
+    name: singlecard e2e test - light
     runs-on: ${{ matrix.os }}
     container:
       image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
@@ -191,37 +192,19 @@ jobs:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
-          pytest -sv tests/e2e/singlecard/test_offline_inference.py
-          pytest -sv tests/e2e/singlecard/test_ilama_lora.py
-          pytest -sv tests/e2e/singlecard/test_guided_decoding.py
-          pytest -sv tests/e2e/singlecard/test_camem.py
-          pytest -sv tests/e2e/singlecard/test_embedding.py
-
-          # ------------------------------------ v1 spec decode test ------------------------------------ #
-          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
-          # TODO: revert me when test_v1_spec_decode.py::test_ngram_correctness is fixed
-          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
+          pytest -sv tests/e2e/singlecard/test_aclgraph.py
+          pytest -sv tests/e2e/singlecard/test_quantization.py
+          pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
 
-          # All other tests, ignore: 310p test, accuracy test.
-          pytest -sv tests/e2e/singlecard/ \
-          --ignore=tests/e2e/singlecard/test_offline_inference.py \
-          --ignore=tests/e2e/singlecard/test_ilama_lora.py \
-          --ignore=tests/e2e/singlecard/test_guided_decoding.py \
-          --ignore=tests/e2e/singlecard/test_camem.py \
-          --ignore=tests/e2e/singlecard/test_embedding.py \
-          --ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py \
-          --ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py \
-          --ignore=tests/e2e/singlecard/test_offline_inference_310p.py \
-          --ignore=tests/e2e/singlecard/models/test_lm_eval_correctness.py
-  e2e-2-cards:
-    needs: [e2e]
-    if: ${{ needs.e2e.result == 'success' }}
+  e2e-2-cards-light:
+    needs: [e2e-light]
+    if: ${{ needs.e2e-light.result == 'success' }}
     strategy:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-2]
-        vllm_version: [main, v0.10.0]
-    name: multicard e2e test
+        vllm_version: [v0.10.2]
+    name: multicard e2e test - light
     runs-on: ${{ matrix.os }}
     container:
       image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
@@ -274,19 +257,4 @@ jobs:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
-          pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py
-          # Fixme: run VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py will raise error.
-          # To avoid oom, we need to run the test in a single process.
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_dbo
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_alltoallv
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_sp_for_qwen3_moe
-          pytest -sv tests/e2e/multicard/test_data_parallel.py
-          pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py \
-            --ignore=tests/e2e/multicard/test_offline_inference_distributed.py \
-            --ignore=tests/e2e/multicard/test_data_parallel.py \
-            --ignore=tests/e2e/multicard/test_offline_inference_310p.py
+          pytest -sv tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP

{vllm_ascend-0.10.0rc1 → vllm_ascend-0.10.2rc1}/.github/workflows/vllm_ascend_test_310p.yaml

@@ -53,7 +53,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-310p-1, linux-aarch64-310p-4]
-        vllm_version: [main, v0.10.0]
+        vllm_version: [v0.10.2]
     name: 310p e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -111,7 +111,7 @@ jobs:
           PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
         run: |
           if [[ "${{ matrix.os }}" == "linux-aarch64-310p-1" ]]; then
-            pytest -sv tests/e2e/singlecard/test_offline_inference_310p.py
+            pytest -sv tests/e2e/310p/test_offline_inference_310p.py
           else
-            pytest -sv tests/e2e/multicard/test_offline_inference_310p.py
-          fi
+            pytest -sv tests/e2e/310p/test_offline_inference_parallel_310p.py
+          fi