vllm-ascend 0.9.2rc1__tar.gz → 0.10.1rc1__tar.gz

vllm_ascend-0.10.1rc1/.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-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/Dockerfile.buildwheel

@@ -14,7 +14,7 @@
 # limitations under the License.
 # This file is a part of the vllm-ascend project.
 #
-ARG PY_VERSION=3.10
+ARG PY_VERSION=3.11
 FROM quay.io/ascend/manylinux:8.0.0-910b-manylinux_2_28-py${PY_VERSION}
 
 ARG COMPILE_CUSTOM_KERNELS=1

{vllm_ascend-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.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-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.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-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/PULL_REQUEST_TEMPLATE.md

@@ -25,4 +25,3 @@ CI passed with new added/existing test.
 If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
 If tests were not added, please describe why they were not added and/or why it was difficult to add.
 -->
-

vllm_ascend-0.10.1rc1/.github/actionlint.yaml

@@ -0,0 +1,17 @@
+self-hosted-runner:
+  # Labels of self-hosted runner in array of strings.
+  labels:
+    - linux-aarch64-a2-0
+    - linux-aarch64-a2-1
+    - linux-aarch64-a2-2
+    - linux-aarch64-a2-4
+    - linux-aarch64-a2-8
+    - linux-arm64-npu-static-8
+    - linux-aarch64-310p-1
+    - 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

{vllm_ascend-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/format_pr_body.sh

@@ -30,6 +30,7 @@ VLLM_VERSION=$2
 VLLM_COMMIT=$3
 OLD=/tmp/orig_pr_body.txt
 NEW=/tmp/new_pr_body.txt
+FINAL=/tmp/final_pr_body.txt
 
 gh pr view --json body --template "{{.body}}" "${PR_NUMBER}" > "${OLD}"
 cp "${OLD}" "${NEW}"
@@ -41,16 +42,18 @@ sed -i '/- vLLM .*$/d' "${NEW}"
     echo ""
     echo "- vLLM version: $VLLM_VERSION"
     echo "- vLLM main: $VLLM_COMMIT"
-    echo ""
 } >> "${NEW}"
 
+# Remove redundant empty lines
+uniq "${NEW}" > "${FINAL}"
+
 # Run this only if ${NEW} is different than ${OLD}
-if ! cmp -s "${OLD}" "${NEW}"; then
+if ! cmp -s "${OLD}" "${FINAL}"; then
     echo
     echo "Updating PR body:"
     echo
     cat "${NEW}"
-    gh pr edit --body-file "${NEW}" "${PR_NUMBER}"
+    gh pr edit --body-file "${FINAL}" "${PR_NUMBER}"
 else
     echo "No changes needed"
 fi

{vllm_ascend-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/workflows/accuracy_test.yaml

@@ -29,35 +29,15 @@ on:
     types: [ labeled ]
   workflow_dispatch:
     inputs:
-      vllm-version:
-        description: 'vllm version:'
-        required: true
-        type: choice
-        # Please also update this when bump matched version
-        # Current supported vLLM versions
-        options:
-          - main
-          - v0.9.2
-          - v0.9.1
-          - v0.7.3
       vllm-ascend-version:
-        description: 'vllm-ascend version:'
+        description: 'vllm-ascend:'
         required: true
         type: choice
+        # Current supported vLLM versions
         options:
+          - latest
           - main
-          - v0.9.1-dev
-          - v0.7.3-dev
-      models:
-        description: 'model:'
-        required: true
-        type: choice
-        options:
-          - all
-          - Qwen/Qwen2.5-VL-7B-Instruct
-          - Qwen/Qwen3-8B-Base
-          - Qwen/Qwen3-30B-A3B
-        default: 'all'
+        default: main
 
 # 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.
@@ -76,58 +56,29 @@ jobs:
     # test will be triggered when tag '*-accuracy-test' & 'ready-for-test' or workflow_dispatch job
     if:  >-
       ${{
-      (contains(github.event.pull_request.labels.*.name, 'accuracy-test') ||
-      contains(github.event.pull_request.labels.*.name, 'vl-accuracy-test') ||
-      contains(github.event.pull_request.labels.*.name, 'moe-accuracy-test') ||
-      contains(github.event.pull_request.labels.*.name, 'dense-accuracy-test')) &&
+      contains(github.event.pull_request.labels.*.name, 'accuracy-test') &&
       contains(github.event.pull_request.labels.*.name, 'ready-for-test') ||
       github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
       }}
-    runs-on: >-
-      ${{
-          (matrix.model_name == 'Qwen/Qwen3-30B-A3B' && 'linux-arm64-npu-4') ||
-          'linux-arm64-npu-2'
-      }}
+    runs-on: ${{ matrix.runner }}
     strategy:
       matrix:
-        # the accuracy test will run:
-        # 1. workflow_dispatch with models input
-        #   - all: Qwen/Qwen3-30B-A3B, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen3-8B-Base
-        #   - specified but not all: Qwen/Qwen3-30B-A3B, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen3-8B-Base
-        # 2. PR labeled with "*-accuracy-test"
-        #   - accuracy-test: Qwen/Qwen3-8B-Base, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen3-30B-A3B
-        #   - dense-accuracy-test: Qwen/Qwen3-8B-Base
-        #   - vl-accuracy-test: Qwen/Qwen2.5-VL-7B-Instruct
-        #   - moe-accuracy-test: Qwen/Qwen3-30B-A3B
-        model_name: ${{ fromJSON(
-          (github.event_name == 'schedule' &&
-            '["Qwen/Qwen3-30B-A3B","Qwen/Qwen2.5-VL-7B-Instruct","Qwen/Qwen3-8B-Base"]') ||
-          (github.event.inputs.models == 'all' &&
-            '["Qwen/Qwen3-30B-A3B","Qwen/Qwen2.5-VL-7B-Instruct","Qwen/Qwen3-8B-Base"]') ||
-          (github.event.inputs.models == 'Qwen/Qwen3-30B-A3B' &&
-            '["Qwen/Qwen3-30B-A3B"]') ||
-          (github.event.inputs.models == 'Qwen/Qwen2.5-VL-7B-Instruct' &&
-            '["Qwen/Qwen2.5-VL-7B-Instruct"]') ||
-          (github.event.inputs.models == 'Qwen/Qwen3-8B-Base' &&
-            '["Qwen/Qwen3-8B-Base"]') ||
-          contains(github.event.pull_request.labels.*.name, 'accuracy-test') &&
-            '["Qwen/Qwen3-8B-Base","Qwen/Qwen2.5-VL-7B-Instruct", "Qwen/Qwen3-30B-A3B"]' ||
-          contains(github.event.pull_request.labels.*.name, 'dense-accuracy-test') &&
-            '["Qwen/Qwen3-8B-Base"]' ||
-          contains(github.event.pull_request.labels.*.name, 'vl-accuracy-test') &&
-            '["Qwen/Qwen2.5-VL-7B-Instruct"]' ||
-          contains(github.event.pull_request.labels.*.name, 'moe-accuracy-test') &&
-            '["Qwen/Qwen3-30B-A3B"]'
-         ) }}
-
+        include:
+          - model_name: Qwen3-8B-Base
+            runner: linux-aarch64-a2-1
+          - model_name: Qwen2.5-VL-7B-Instruct
+            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
     container:
-      image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
       env:
-        DATASET_SOURCE: ModelScope
         VLLM_USE_MODELSCOPE: True
-        USE_MODELSCOPE_HUB: 1
         # 1. If version specified (work_dispatch), do specified branch accuracy test
         # 2. If no version (labeled PR), do accuracy test by default ref:
         # The branch, tag or SHA to checkout. When checking out the repository that
@@ -139,18 +90,18 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
-      - name: Check npu and CANN info
+      - name: Set model name as output
+        id: set_output
         run: |
-          npu-smi info
-          cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
+          echo "model_name=${{ matrix.model_name }}" >> $GITHUB_OUTPUT
 
       - name: Config mirrors
         run: |
-          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
+          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
           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: Install system dependencies
         run: |
@@ -161,13 +112,30 @@ jobs:
         uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
+          ref: v0.10.1.1
           path: ./vllm-empty
-          # Please also update this when bump matched version
-          ref: ${{ github.event.inputs.vllm-version || 'v0.9.2' }}
 
       - name: Install vllm-project/vllm from source
         working-directory: ./vllm-empty
-        run: VLLM_TARGET_DEVICE=empty pip install -e .
+        run: |
+          VLLM_TARGET_DEVICE=empty pip install -e .
+
+      - name: Resolve vllm-ascend version
+        run: |
+          VERSION_INPUT="${{ github.event.inputs.vllm-ascend-version }}"
+          
+          if [[ "$VERSION_INPUT" == "latest" ]]; then
+            TAGS=$(git ls-remote --tags --sort=-v:refname https://github.com/vllm-project/vllm-ascend "v*" | cut -f2 | sed 's|refs/tags/||')
+            LATEST_TAG=$(echo "$TAGS" | head -n1)
+            if [[ -z "$LATEST_TAG" ]]; then
+              RESOLVED_VERSION="main"
+            else
+              RESOLVED_VERSION="$LATEST_TAG"
+            fi
+          else
+            RESOLVED_VERSION="$VERSION_INPUT"
+          fi
+          echo "GHA_VLLM_ASCEND_VERSION=$RESOLVED_VERSION" >> $GITHUB_ENV
 
       - name: Checkout vllm-project/vllm-ascend repo
         uses: actions/checkout@v4
@@ -182,8 +150,8 @@ jobs:
           PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
         run: |
           pip install -r requirements-dev.txt
-          pip install -v -e . 
-            
+          pip install -v -e .
+
       - name: Get vLLM commit hash and URL
         working-directory: ./vllm-empty
         run: |
@@ -196,15 +164,6 @@ jobs:
           VLLM_ASCEND_COMMIT=$(git rev-parse --short=7 HEAD)
           echo "VLLM_ASCEND_COMMIT=$VLLM_ASCEND_COMMIT" >> $GITHUB_ENV
 
-      - name: Print resolved hashes
-        run: |
-          echo "vLLM       : ${{ env.VLLM_COMMIT }}"
-          echo "vLLM-Ascend: ${{ env.VLLM_ASCEND_COMMIT }}"
-
-      - name: Install lm-eval, ray, and datasets
-        run: |
-            pip install lm-eval==0.4.8
-
       - name: Collect version info
         run: |
           for dir in /usr/local/Ascend/ascend-toolkit/*; do
@@ -224,39 +183,27 @@ jobs:
             pip show torch | grep "Version:" | awk '{print "GHA_TORCH_VERSION="$2}'
             pip show torch_npu | grep "Version:" | awk '{print "GHA_TORCH_NPU_VERSION="$2}'
             pip show vllm | grep "Version:" | awk '{print "GHA_VLLM_VERSION="$2}' | sed 's/+.*//'
-            echo "GHA_VLLM_ASCEND_VERSION=${{ github.event.inputs.vllm-ascend-version || github.ref }}"
           } >> "$GITHUB_ENV"
-      
-      - name: Print versions
-        run: |
-          echo "CANN: ${{ env.GHA_CANN_VERSION }}"
-          echo "Torch NPU: ${{ env.GHA_TORCH_NPU_VERSION }}"
-          echo "Torch: ${{ env.GHA_TORCH_VERSION }}"
-          echo "vLLM: ${{ env.GHA_VLLM_VERSION }}"
-          echo "vLLM Ascend: ${{ env.GHA_VLLM_ASCEND_VERSION }}"
 
-      - name: Run Accuracy Test
+      - name: Run accuracy test
         id: report
-        working-directory: ./benchmarks
         env:
-          PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+          VLLM_USE_MODELSCOPE: True
+          VLLM_VERSION: ${{ env.GHA_VLLM_VERSION }}
+          VLLM_COMMIT: ${{ env.VLLM_COMMIT }}
+          VLLM_ASCEND_VERSION: ${{ env.GHA_VLLM_ASCEND_VERSION || github.ref }}
+          VLLM_ASCEND_COMMIT: ${{ env.VLLM_ASCEND_COMMIT }}
+          CANN_VERSION: ${{ env.GHA_CANN_VERSION }}
+          TORCH_VERSION: ${{ env.GHA_TORCH_VERSION }}
+          TORCH_NPU_VERSION: ${{ env.GHA_TORCH_NPU_VERSION }}
         run: |
           model_base_name=$(basename ${{ matrix.model_name }})
           markdown_name="${model_base_name}"
-          echo "markdown_name=$markdown_name"
           echo "markdown_name=$markdown_name" >> $GITHUB_OUTPUT
-          mkdir -p ./accuracy
-
-          python ./scripts/run_accuracy.py \
-            --model "${{ matrix.model_name }}" \
-            --output "./accuracy/${markdown_name}.md" \
-            --vllm_ascend_version "${{ env.GHA_VLLM_ASCEND_VERSION || github.ref }}" \
-            --cann_version "${{ env.GHA_CANN_VERSION }}" \
-            --torch_npu_version "${{ env.GHA_TORCH_NPU_VERSION }}" \
-            --torch_version "${{ env.GHA_TORCH_VERSION }}" \
-            --vllm_version "${{ env.GHA_VLLM_VERSION }}" \
-            --vllm_commit "${{ env.VLLM_COMMIT }}" \
-            --vllm_ascend_commit "${{ env.VLLM_ASCEND_COMMIT }}" \
+          mkdir -p ./benchmarks/accuracy
+          pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py \
+          --config ./tests/e2e/models/configs/${{ matrix.model_name }}.yaml
 
       - name: Generate step summary
         if: ${{ always() }}
@@ -268,19 +215,7 @@ jobs:
           SAFE_VLLM_ASCEND_VERSION="${GHA_VLLM_ASCEND_VERSION//\//-}"
           echo "SAFE_VLLM_ASCEND_VERSION=$SAFE_VLLM_ASCEND_VERSION" >> "$GITHUB_ENV"
 
-      - name: Check report first line for failure
-        id: check_report
-        run: |
-          REPORT_PATH="./benchmarks/accuracy/${{ steps.report.outputs.markdown_name }}.md"
-          echo "Scanning $REPORT_PATH for ❌ …"
-          if grep -q '❌' "$REPORT_PATH"; then
-            echo "contains_fail=true" >> $GITHUB_OUTPUT
-          else
-            echo "contains_fail=false" >> $GITHUB_OUTPUT
-          fi
-
       - name: Upload Report 
-        if: ${{ github.event_name == 'workflow_dispatch' && steps.check_report.outputs.contains_fail == 'false' }}
         uses: actions/upload-artifact@v4
         with:
           name: "report-${{ env.SAFE_VLLM_ASCEND_VERSION }}-${{ steps.report.outputs.markdown_name }}"
@@ -289,10 +224,14 @@ jobs:
           retention-days: 90
           overwrite: true
 
+    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' }}
+    if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}
     env:
       UPSTREAM_REPO: vllm-project/vllm-ascend
     steps:
@@ -302,7 +241,7 @@ jobs:
           repository: vllm-ascend-ci/vllm-ascend
           token: ${{ secrets.PAT_TOKEN }}
           ref: main
-
+      
       - name: Add upstream remote
         run: |
           git remote add upstream https://github.com/${{ env.UPSTREAM_REPO }}.git
@@ -319,10 +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-*
@@ -334,7 +273,7 @@ jobs:
           find ./docs/source/developer_guide/evaluation/accuracy_report -maxdepth 1 -type f -name '*.md' ! -name 'index.md' -delete
           find ./docs/source/developer_guide/evaluation/accuracy_report -mindepth 2 -type f -name '*.md' -exec mv -f {} ./docs/source/developer_guide/evaluation/accuracy_report \;
           find ./docs/source/developer_guide/evaluation/accuracy_report -mindepth 1 -type d -empty -delete
-
+      
       - name: Update accuracy_report/index.md
         run: |
           REPORT_DIR="./docs/source/developer_guide/evaluation/accuracy_report"
@@ -360,7 +299,7 @@ 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
@@ -372,18 +311,12 @@ 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:
-            ${{ 
-              github.event.inputs.models == 'all' 
-                && 'All models (Qwen/Qwen3-30B-A3B, Qwen2.5-VL-7B-Instruct, Qwen3-8B-Base)' 
-                || github.event.inputs.models 
-            }}
-            
-            - [Workflow run][1]
+              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)
             
-            [1]: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}`
+              - [Workflow run][1]
+              
+              [1]: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}`
             });
             core.info(`Created PR #${pr.data.number}`);
- 

{vllm_ascend-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.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-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/workflows/image_310p_openeuler.yml

@@ -6,10 +6,10 @@ name: 'image / openEuler / 310p'
 #   - push: ${{ github.event_name != 'pull_request' }} ==> false
 # 2. branches push trigger image publish
 #   - is for branch/dev/nightly image
-#   - commits are merge into main/*-dev  ==> vllm-ascend:main / vllm-ascend:*-dev
+#   - commits are merge into main/*-dev  ==> vllm-ascend:main-310p-openeuler / vllm-ascend:*-dev-310p-openeuler
 # 3. tags push trigger image publish
 #   - is for final release image
-#   - Publish when tag with v* (pep440 version)  ===>  vllm-ascend:v1.2.3-openeuler|latest / vllm-ascend:v1.2.3rc1-openeuler
+#   - Publish when tag with v* (pep440 version)  ===>  vllm-ascend:v1.2.3-310p-openeuler / vllm-ascend:v1.2.3rc1-310p-openeuler
 on:
   pull_request:
     branches:
@@ -33,9 +33,15 @@ on:
     tags:
       - 'v*'
     paths:
-      - '.github/workflows/image_310p.openeuler.yml'
+      - '.github/workflows/image_310p_openeuler.yml'
       - 'Dockerfile.310p.openEuler'
       - 'vllm_ascend/**'
+      - 'setup.py'
+      - 'pyproject.toml'
+      - 'requirements.txt'
+      - 'cmake/**'
+      - 'CMakeLists.txt'
+      - 'csrc/**'
 
 jobs:
   build:
@@ -63,16 +69,18 @@ jobs:
         # Note for test case
         # https://github.com/marketplace/actions/docker-metadata-action#typeref
         # 1. branch job pulish per main/*-dev branch commits
-        # 2. main and dev pull_request is build only, so the tag pr-N-openeuler is fine
+        # 2. main and dev pull_request is build only, so the tag pr-N-310p-openeuler is fine
         # 3. only pep440 matched tag will be published:
-        #    - v0.7.1 --> v0.7.1-openeuler, latest
-        #    - pre/post/dev: v0.7.1rc1-openeuler/v0.7.1rc1-openeuler/v0.7.1rc1.dev1-openeuler/v0.7.1.post1-openeuler, no latest
+        #    - v0.7.1 --> v0.7.1-310p-openeuler
+        #    - pre/post/dev: v0.7.1rc1-310p-openeuler/v0.7.1rc1-310p-openeuler/v0.7.1rc1.dev1-310p-openeuler/v0.7.1.post1-310p-openeuler, no latest
         #      which follow the rule from vLLM with prefix v
         # TODO(yikun): the post release might be considered as latest release
         tags: |
           type=ref,event=branch,suffix=-310p-openeuler
-          type=ref,event=pr,suffix=-openeuler
+          type=ref,event=pr,suffix=-310p-openeuler
           type=pep440,pattern={{raw}},suffix=-310p-openeuler
+        flavor:
+          latest=false
 
     - name: Free up disk space
       uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
@@ -112,3 +120,4 @@ jobs:
         file: Dockerfile.310p.openEuler
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+        provenance: false

{vllm_ascend-0.9.2rc1 → vllm_ascend-0.10.1rc1}/.github/workflows/image_310p_ubuntu.yml

@@ -6,10 +6,10 @@ name: 'image / Ubuntu / 310p'
 #   - push: ${{ github.event_name != 'pull_request' }} ==> false
 # 2. branches push trigger image publish
 #   - is for branch/dev/nightly image
-#   - commits are merge into main/*-dev  ==> vllm-ascend:main / vllm-ascend:*-dev
+#   - commits are merge into main/*-dev  ==> vllm-ascend:main-310p / vllm-ascend:*-dev-310p
 # 3. tags push trigger image publish
 #   - is for final release image
-#   - Publish when tag with v* (pep440 version)  ===>  vllm-ascend:v1.2.3|latest / vllm-ascend:v1.2.3rc1
+#   - Publish when tag with v* (pep440 version)  ===>  vllm-ascend:v1.2.3-310p / vllm-ascend:v1.2.3rc1-310p
 on:
   pull_request:
     branches:
@@ -36,6 +36,12 @@ on:
       - '.github/workflows/image_310p_ubuntu.yml'
       - 'Dockerfile.310p'
       - 'vllm_ascend/**'
+      - 'setup.py'
+      - 'pyproject.toml'
+      - 'requirements.txt'
+      - 'cmake/**'
+      - 'CMakeLists.txt'
+      - 'csrc/**'
 jobs:
 
   build:
@@ -61,14 +67,16 @@ jobs:
         # 1. branch job pulish per main/*-dev branch commits
         # 2. main and dev pull_request is build only, so the tag pr-N is fine
         # 3. only pep440 matched tag will be published:
-        #    - v0.7.1 --> v0.7.1, latest
-        #    - pre/post/dev: v0.7.1rc1/v0.7.1rc1/v0.7.1rc1.dev1/v0.7.1.post1, no latest
+        #    - v0.7.1 --> v0.7.1-310p
+        #    - pre/post/dev: v0.7.1rc1-310p/v0.7.1rc1-310p/v0.7.1rc1.dev1-310p/v0.7.1.post1-310p, no latest
         #      which follow the rule from vLLM with prefix v
         # TODO(yikun): the post release might be considered as latest release
         tags: |
           type=ref,event=branch,suffix=-310p
           type=ref,event=pr,suffix=-310p
           type=pep440,pattern={{raw}},suffix=-310p
+        flavor:
+          latest=false
 
     - name: Free up disk space
       uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
@@ -108,3 +116,4 @@ jobs:
         tags: ${{ steps.meta.outputs.tags }}
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+        provenance: false