[CI] Update vLLM to v0.11.0 (#3315)

### What this PR does / why we need it?
There are 3 step to upgrade vllm-ascend to newest vllm. We'll create 3
PR

- [x] Upgrade vllm to v0.11.0 to make CI happy first .
- [ ] Move deepseek v3.2 to vllm way
- [ ] Then we'll add a new PR to add vllm main support.

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.11.0

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

.github/workflows/accuracy_test.yaml

@@ -112,7 +112,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
-          ref: v0.11.0rc3
+          ref: v0.11.0
           path: ./vllm-empty
 
       - name: Install vllm-project/vllm from source

.github/workflows/format_pr_body.yaml

@@ -36,7 +36,7 @@ jobs:
 
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=releases/v0.11.0
+          VLLM_COMMIT=v0.11.0
           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: v0.11.0rc3
+          - vllm_branch: v0.11.0
             vllm_ascend_branch: main
             vllm_use_v1: 1
       max-parallel: 1

.github/workflows/vllm_ascend_dist.yaml

@@ -43,7 +43,7 @@ jobs:
     strategy:
       matrix:
         os: [linux-aarch64-a3-8]
-        vllm_version: [v0.11.0rc3]
+        vllm_version: [v0.11.0]
     name: vLLM Ascend test
     runs-on: ${{ matrix.os }}
     container:

.github/workflows/vllm_ascend_test.yaml

@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/pre-commit.yml
     with:
-      vllm: releases/v0.11.0
+      vllm: v0.11.0
 
   changes:
     runs-on: ubuntu-latest
@@ -83,7 +83,7 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [releases/v0.11.0, v0.11.0rc3]
+        vllm_version: [v0.11.0]
     steps:
       - name: Install packages
         run: |
@@ -145,7 +145,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [releases/v0.11.0, v0.11.0rc3]
+        vllm_version: [v0.11.0]
     # 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.

.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: [v0.11.0rc3]
+        vllm_version: [v0.11.0]
     name: 310p e2e test
     runs-on: ${{ matrix.os }}
     container:

.github/workflows/vllm_ascend_test_full.yaml

@@ -68,7 +68,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [releases/v0.11.0, v0.11.0rc3]
+        vllm_version: [v0.11.0]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml

.github/workflows/vllm_ascend_test_full_vllm_0.11.0.yaml

@@ -45,7 +45,7 @@ jobs:
   e2e-test:
     uses: ./.github/workflows/_e2e_test.yaml
     with:
-      vllm: releases/v0.11.0
+      vllm: v0.11.0
       runner: linux-aarch64-a2
       image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
       type: full

Dockerfile

@@ -37,7 +37,7 @@ 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=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 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/ --extra-index https://download.pytorch.org/whl/cpu/ && \

Dockerfile.310p

@@ -37,7 +37,7 @@ 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=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 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/ --extra-index https://download.pytorch.org/whl/cpu/ && \

Dockerfile.310p.openEuler

@@ -34,7 +34,7 @@ COPY . /vllm-workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 
 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.

Dockerfile.a3

@@ -37,7 +37,7 @@ 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=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 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/ --extra-index https://download.pytorch.org/whl/cpu/ && \

Dockerfile.a3.openEuler

@@ -34,7 +34,7 @@ COPY . /vllm-workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 
 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.

Dockerfile.openEuler

@@ -34,7 +34,7 @@ COPY . /vllm-workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.11.0rc3
+ARG VLLM_TAG=v0.11.0
 
 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.

vllm_ascend/models/deepseek_v2.py

@@ -422,7 +422,10 @@ class CustomDeepseekV2SFAAttention(DeepseekV2MLAAttention):
 
 class CustomDeepseekV2DecoderLayer(DeepseekV2DecoderLayer):
 
-    def __init__(self, vllm_config: VllmConfig, prefix: str) -> None:
+    def __init__(self,
+                 vllm_config: VllmConfig,
+                 prefix: str,
+                 topk_indices_buffer=None) -> None:
         nn.Module.__init__(self)
         config = vllm_config.model_config.hf_config
         model_config = vllm_config.model_config