upgrade vLLM to 0.12.0 branch

wangxiyuan · wangxiyuan · commit 7f2ade423365 · 2025-12-02T22:16:14.000+08:00
Signed-off-by: wangxiyuan &lt;wangxiyuan1007@gmail.com&gt;
diff --git 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: "86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24"
+        default: "releases/v0.12.0"
         type: string
         description: vllm version to use
       vllm_ascend_remote_url:
diff --git a/.github/workflows/format_pr_body.yaml b/.github/workflows/format_pr_body.yaml
@@ -36,7 +36,7 @@ jobs:
 
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+          VLLM_COMMIT=releases/v0.12.0
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository
diff --git a/.github/workflows/nightly_benchmarks.yaml b/.github/workflows/nightly_benchmarks.yaml
@@ -51,7 +51,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+          - vllm_branch: releases/v0.12.0
             vllm_ascend_branch: main
       max-parallel: 1
     container:
diff --git a/.github/workflows/vllm_ascend_test_nightly_a2.yaml b/.github/workflows/vllm_ascend_test_nightly_a2.yaml
@@ -86,7 +86,7 @@ jobs:
             tests: tests/e2e/nightly/ops
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: releases/v0.12.0
       runner: ${{ matrix.test_config.os }}
       tests: ${{ matrix.test_config.tests }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a2'
@@ -134,7 +134,7 @@ jobs:
               - Qwen3-Next-80B-A3B-Instruct
     uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: releases/v0.12.0
       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:8.3.rc2-910b-ubuntu22.04-py3.11'
diff --git a/.github/workflows/vllm_ascend_test_nightly_a3.yaml b/.github/workflows/vllm_ascend_test_nightly_a3.yaml
@@ -139,7 +139,7 @@ jobs:
             tests: tests/e2e/nightly/models/test_glm4_5.py
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: releases/v0.12.0
       runner: ${{ matrix.test_config.os }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
       tests: ${{ matrix.test_config.tests }}
diff --git a/.github/workflows/vllm_ascend_test_pr_full.yaml b/.github/workflows/vllm_ascend_test_pr_full.yaml
@@ -69,7 +69,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
+        vllm_version: [releases/v0.12.0]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml
diff --git a/.github/workflows/vllm_ascend_test_pr_light.yaml b/.github/workflows/vllm_ascend_test_pr_light.yaml
@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/pre-commit.yml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: releases/v0.12.0
   changes:
     runs-on: ubuntu-latest
     outputs:
@@ -84,7 +84,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
+        vllm_version: [releases/v0.12.0]
     steps:
       - name: Install packages
         run: |
@@ -142,7 +142,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
+        vllm_version: [releases/v0.12.0]
     # 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.
diff --git a/.github/workflows/vllm_ascend_test_report.yaml b/.github/workflows/vllm_ascend_test_report.yaml
@@ -72,7 +72,7 @@ jobs:
               - DeepSeek-V2-Lite
     uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: releases/v0.12.0
       runner: ${{ matrix.runner }}
       image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       model_list: ${{ toJson(matrix.model_list) }}
diff --git a/Dockerfile b/Dockerfile
@@ -48,10 +48,8 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/Dockerfile.310p b/Dockerfile.310p
@@ -39,10 +39,8 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/Dockerfile.310p.openEuler b/Dockerfile.310p.openEuler
@@ -36,10 +36,8 @@ COPY . /vllm-workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/Dockerfile.a3 b/Dockerfile.a3
@@ -47,10 +47,8 @@ RUN apt-get update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/Dockerfile.a3.openEuler b/Dockerfile.a3.openEuler
@@ -50,10 +50,8 @@ RUN yum update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/Dockerfile.openEuler b/Dockerfile.openEuler
@@ -50,10 +50,8 @@ RUN yum update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
-# Revert this change once VLLM_TAG is specified to branch or tag
-# RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
-RUN git clone $VLLM_REPO /vllm-workspace/vllm && (cd /vllm-workspace/vllm && git checkout $VLLM_TAG)
+ARG VLLM_TAG=releases/v0.12.0
+RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
diff --git a/docs/source/community/versioning_policy.md b/docs/source/community/versioning_policy.md
@@ -43,7 +43,7 @@ The table below is the release compatibility matrix for vLLM Ascend release.
 For main branch of vLLM Ascend, we usually make it compatible with the latest vLLM release and a newer commit hash of vLLM. Please note that this table is usually updated. Please check it regularly.
 | vLLM Ascend | vLLM         | Python           | Stable CANN | PyTorch/torch_npu  |
 |-------------|--------------|------------------|-------------|--------------------|
-|     main    | v0.11.2 | >= 3.10, < 3.12   | 8.3.RC1 | 2.7.1 / 2.7.1 |
+|     main    | releases/v0.12.0 branch | >= 3.10, < 3.12   | 8.3.RC1 | 2.7.1 / 2.7.1 |
 
 ## Release cadence
 
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -77,7 +77,7 @@
     # CANN image tag
     'cann_image_tag': "8.3.rc2-910b-ubuntu22.04-py3.11",
     # vllm version in ci
-    'ci_vllm_version': '86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24',
+    'ci_vllm_version': 'releases/v0.12.0',
 }
 
 # For cross-file header anchors
