[Main2Main][Deps][Misc] Upgrade vLLM to v0.15.0 (#6470)

### What this PR does / why we need it? This PR upgrades the vLLM dependency from `v0.14.1` to `v0.15.0`. This involves: - Updating the `VLLM_TAG` in all `Dockerfile`. - Updating the vLLM version in `docs/source/conf.py`. - Removing conditional code paths specific to `v0.14.1` across the codebase, which simplifies maintenance. - Fix `TypeError: MMEncoderAttention.__init__() got an unexpected keyword argument 'multimodal_config'` due to https://github.com/vllm-project/vllm/pull/31972. - Fix `_shared_experts: 'NoneType' object is not callable` due to https://github.com/vllm-project/vllm/pull/32082 by https://github.com/vllm-project/vllm-ascend/pull/6335. - Fix `ReshapeAndCacheOperation setup failed!` due to https://github.com/vllm-project/vllm/pull/25954 by overriding attention metadata slots. This upgrade is necessary to keep the project aligned with the latest features, bug fixes, and API changes in the vLLM project. ### Does this PR introduce _any_ user-facing change? No, this is an internal dependency update and does not introduce any user-facing changes. ### How was this patch tested? CI is expected to pass with these changes, ensuring that all existing tests are successful with the new vLLM version. - vLLM version: v0.14.1 - vLLM main: dc917cceb8 co-authored-by: shen-shanshan <467638484@qq.com> --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2026-02-02 15:57:55 +08:00
parent d53510b26d
commit eeedf7c503
32 changed files with 81 additions and 108 deletions
--- a/.github/workflows/_e2e_nightly_multi_node.yaml
+++ b/.github/workflows/_e2e_nightly_multi_node.yaml
@@ -32,7 +32,7 @@ on:
        description: how many pods will be pulled up via lws.yaml, indicates number of nodes we need
      vllm_version:
        required: false
-        default: "v0.14.1"
+        default: "v0.15.0"
        type: string
        description: vllm version to use
      vllm_ascend_remote_url:
@@ -78,7 +78,7 @@ jobs:
        - name: Decode kubeconfig from secrets
          run: |
            # Decode and save kubeconfig
-            echo "${{ secrets.KUBECONFIG_B64 }}" | base64 -d > $KUBECONFIG
+            echo "${{ secrets.KUBECONFIG_B64 }}" | base64 -d > "$KUBECONFIG"

        - name: Checkout code
          uses: actions/checkout@v6
@@ -133,7 +133,7 @@ jobs:
            image="${{ inputs.image }}"
            config_file_path="${{ inputs.config_file_path }}"
            fail_tag=FAIL_TAG_"${{ inputs.config_file_path }}"
-            echo "FAIL_TAG=${fail_tag}" >> $GITHUB_ENV
+            echo "FAIL_TAG=${fail_tag}" >> "$GITHUB_ENV"

            required_params=("size" "replicas" "image" "config_file_path")
            for param in "${required_params[@]}"; do
@@ -264,5 +264,5 @@ jobs:
        - name: Post process
          if: always()
          run: |
-            kubectl get pods -n $NAMESPACE --ignore-not-found=true
+            kubectl get pods -n "$NAMESPACE" --ignore-not-found=true
            kubectl delete -f ./lws.yaml --ignore-not-found=true || true
--- a/.github/workflows/bot_pr_create.yaml
+++ b/.github/workflows/bot_pr_create.yaml
@@ -37,8 +37,8 @@ jobs:
    steps:
      - name: Get vLLM version
        run: |
-          VLLM_COMMIT=dc917cceb877dfd13f98c538c4c96158047d98bd
-          echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
+          VLLM_COMMIT=v0.15.0
+          echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> "$GITHUB_ENV"

      - name: Checkout repository
        uses: actions/checkout@0c366fd6a839edf440554fa01a7085ccba70ac98 # v4.2.2
@@ -49,7 +49,7 @@ jobs:
      - name: Get vLLM release version
        run: |
          VLLM_VERSION=$(python3 docs/source/conf.py | jq .ci_vllm_version | tr -d '"')
-          echo "VLLM_VERSION=$VLLM_VERSION" >> $GITHUB_ENV
+          echo "VLLM_VERSION=$VLLM_VERSION" >> "$GITHUB_ENV"

      - name: Update PR description
        env:
--- a/.github/workflows/dockerfiles/Dockerfile.lint
+++ b/.github/workflows/dockerfiles/Dockerfile.lint
@@ -27,7 +27,7 @@ RUN apt-get update -y && \

 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 # For lint purpose, actually we need make a main2main matching.
-ARG VLLM_COMMIT=dc917cceb877dfd13f98c538c4c96158047d98bd
+ARG VLLM_COMMIT=v0.15.0
 RUN git clone $VLLM_REPO /vllm-workspace/vllm && \
    cd /vllm-workspace/vllm && \
    git checkout $VLLM_COMMIT
--- a/.github/workflows/pr_test_full.yaml
+++ b/.github/workflows/pr_test_full.yaml
@@ -75,7 +75,7 @@ jobs:
    name: e2e-full
    strategy:
      matrix:
-        vllm_version: [dc917cceb877dfd13f98c538c4c96158047d98bd, v0.14.1]
+        vllm_version: [v0.15.0]
    needs: [changes]
    if: ${{ needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.e2e_tracker == true }}
    uses: ./.github/workflows/_e2e_test.yaml
--- a/.github/workflows/pr_test_light.yaml
+++ b/.github/workflows/pr_test_light.yaml
@@ -41,7 +41,7 @@ jobs:
  lint:
    uses: ./.github/workflows/_pre_commit.yml
    with:
-      vllm: dc917cceb877dfd13f98c538c4c96158047d98bd
+      vllm: v0.15.0
  changes:
    runs-on: linux-aarch64-a2-0
    outputs:
@@ -87,7 +87,7 @@ jobs:
    if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
    strategy:
      matrix:
-        vllm_version: [dc917cceb877dfd13f98c538c4c96158047d98bd, v0.14.1]
+        vllm_version: [v0.15.0]
    uses: ./.github/workflows/_unit_test.yaml
    with:
      vllm: ${{ matrix.vllm_version }}
@@ -99,7 +99,7 @@ jobs:
    name: e2e-light
    strategy:
      matrix:
-        vllm_version: [dc917cceb877dfd13f98c538c4c96158047d98bd, v0.14.1]
+        vllm_version: [v0.15.0]
    # Note (yikun): If CI resource are limited we can split job into two chain jobs
    needs: [lint, changes]
    # only trigger e2e test after lint passed and the change is e2e related with pull request.
--- a/.github/workflows/schedule_codecov_refresh.yaml
+++ b/.github/workflows/schedule_codecov_refresh.yaml
@@ -33,7 +33,7 @@ jobs:
    name: refresh codecov
    strategy:
      matrix:
-        vllm_version: [dc917cceb877dfd13f98c538c4c96158047d98bd]
+        vllm_version: [v0.15.0]
    uses: ./.github/workflows/_unit_test.yaml
    with:
      vllm: ${{ matrix.vllm_version }}
--- a/.github/workflows/schedule_nightly_test_a2.yaml
+++ b/.github/workflows/schedule_nightly_test_a2.yaml
@@ -133,7 +133,7 @@ jobs:
              - Qwen3-Omni-30B-A3B-Instruct
    uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
    with:
-      vllm: v0.14.1
+      vllm: v0.15.0
      runner: ${{ matrix.test_config.os }}
      model_list: ${{ toJson(matrix.test_config.model_list) }}
      image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11'
--- a/.github/workflows/schedule_test_benchmarks.yaml
+++ b/.github/workflows/schedule_test_benchmarks.yaml
@@ -51,7 +51,7 @@ jobs:
    strategy:
      matrix:
        include:
-          - vllm_branch: v0.14.1
+          - vllm_branch: v0.15.0
            vllm_ascend_branch: main
      max-parallel: 1
    container:
@@ -130,7 +130,7 @@ jobs:
      - name: Generate step summary
        if: github.event_name != 'schedule' && github.event_name != 'workflow_dispatch'
        run: |
-          cat ./benchmarks/results/benchmark_results.md >> $GITHUB_STEP_SUMMARY
+          cat ./benchmarks/results/benchmark_results.md >> "$GITHUB_STEP_SUMMARY"

      - name: Upload benchmark artifacts
        if: github.event_name != 'schedule' && github.event_name != 'workflow_dispatch'
@@ -172,9 +172,9 @@ jobs:
            commit_id=${line%% *}
            commit_title=${line#* }

-            git checkout $commit_id
-            commit_time=$(git show -s --format=%cd $commit_hash --date=iso-strict)
-            commit_time_no_tz=${commit_time::19}
+            git checkout "$commit_id"
+            commit_time=$(git show -s --format=%cd "$commit_id" --date=iso-strict)
+            commit_time_no_tz="${commit_time::19}"
            pip install -e .

            echo "------------------------"
@@ -191,9 +191,9 @@ jobs:
              ERROR_MSG="Benchmark failed to run"
            fi
            # send the result to es
-            escli add --vllm_branch ${{ matrix.vllm_branch }} \
-            --vllm_ascend_branch ${{ matrix.vllm_ascend_branch }} \
-            --commit_id $commit_id \
+            escli add --vllm_branch "${{ matrix.vllm_branch }}" \
+            --vllm_ascend_branch "${{ matrix.vllm_ascend_branch }}" \
+            --commit_id "$commit_id" \
            --commit_title "$commit_title" \
            --created_at "$commit_time_no_tz" \
            --res_dir ./benchmarks/results \