upgrade vLLM to main (#4608)

1. fix vllm-project/vllm#28542
The model structure modifications we involved in are:
     - Qwen2.5-VL(still exist some patch)
     - Qwen2-VL
     - Qwen2
     - DeepSeek series
     - Qwen-moe series
2. fix vllm-project/vllm#29121
   the output token now  type changed from np to `list[list[int]]`

3. fix vllm-project/vllm#29262
    `xformers` backend for multimodal now has been deprecated
4. fix vllm-project/vllm#29342

5. fix vllm-project/vllm#28579
6. fix vllm-project/vllm#28718
7. fix vllm-project/vllm#28665
8. fix vllm-project/vllm#26847
vllm introduced the `optimization-level`, some default config has been
changed, and the param `--enforce-eager` has been deprecated
9. fix http://github.com/vllm-project/vllm/pull/29223 it retuns tuple
for sampler.
10. fix vllm-project/vllm#29471 we'll remove the
related patch to avoid this kind of error.

Co-authored-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: wangli <wangli858794774@gmail.com>


- vLLM version: v0.11.2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: wangli <wangli858794774@gmail.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>

Author: 3 people

.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: "v0.11.2"
+        default: "86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24"
         type: string
         description: vllm version to use
       vllm_ascend_remote_url:

.github/workflows/format_pr_body.yaml

@@ -36,7 +36,7 @@ jobs:
 
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=v0.11.2
+          VLLM_COMMIT=86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository

.github/workflows/nightly_benchmarks.yaml

@@ -51,7 +51,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: v0.11.2
+          - vllm_branch: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
             vllm_ascend_branch: main
       max-parallel: 1
     container:

.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: v0.11.2
+      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
       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: v0.11.2
+      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
       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'

.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: v0.11.2
+      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
       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 }}

.github/workflows/vllm_ascend_test_pr_full.yaml

@@ -69,7 +69,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [v0.11.2]
+        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml

.github/workflows/vllm_ascend_test_pr_light.yaml

@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/pre-commit.yml
     with:
-      vllm: v0.11.2
+      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
   changes:
     runs-on: ubuntu-latest
     outputs:
@@ -84,7 +84,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [v0.11.2]
+        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
     steps:
       - name: Install packages
         run: |
@@ -142,7 +142,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [v0.11.2]
+        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
     # 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.

.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: v0.11.2
+      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
       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) }}

Dockerfile

@@ -48,8 +48,10 @@ 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=v0.11.2
-RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
+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)
 # 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 && \

Dockerfile.310p

@@ -39,8 +39,10 @@ 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=v0.11.2
-RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
+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)
 # 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 && \