[CI] fix ci

.github/workflows/accuracy_test.yaml

@@ -88,7 +88,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
 
       - name: Set model name as output
         id: set_output
@@ -109,7 +109,7 @@ jobs:
           apt-get -y install gcc g++ cmake libnuma-dev
 
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           ref: v0.10.0
@@ -138,7 +138,7 @@ jobs:
           echo "GHA_VLLM_ASCEND_VERSION=$RESOLVED_VERSION" >> $GITHUB_ENV
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm-ascend
           path: ./vllm-ascend
@@ -236,7 +236,7 @@ jobs:
       UPSTREAM_REPO: vllm-project/vllm-ascend
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-ascend-ci/vllm-ascend
           token: ${{ secrets.PAT_TOKEN }}

.github/workflows/format_pr_body.yaml

@@ -34,7 +34,7 @@ jobs:
 
     steps:
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           path: ./vllm-empty

.github/workflows/image_310p_openeuler.yml

@@ -53,7 +53,7 @@ jobs:
           'ubuntu-24.04-arm'
       }}
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/image_310p_ubuntu.yml

@@ -49,7 +49,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/image_a3_openeuler.yml

@@ -53,7 +53,7 @@ jobs:
           'ubuntu-24.04-arm'
       }}
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/image_a3_ubuntu.yml

@@ -49,7 +49,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/image_openeuler.yml

@@ -52,7 +52,7 @@ jobs:
           'ubuntu-24.04-arm'
       }}
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/image_ubuntu.yml

@@ -49,7 +49,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v4
 
     - name: Print
       run: |

.github/workflows/nightly_benchmarks.yaml

@@ -97,12 +97,12 @@ jobs:
           git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           path: ./vllm-empty

.github/workflows/pre-commit.yml

@@ -11,14 +11,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Checkout vllm-project/vllm-ascend repo
-      uses: actions/checkout@v5
+      uses: actions/checkout@v4
     - uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
       with:
         python-version: "3.11"
     - run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
     - run: echo "::add-matcher::.github/workflows/matchers/mypy.json"
     - name: Checkout vllm-project/vllm repo
-      uses: actions/checkout@v5
+      uses: actions/checkout@v4
       with:
         repository: vllm-project/vllm
         path: ./vllm-empty

.github/workflows/vllm_ascend_doctest.yaml

@@ -66,7 +66,7 @@ jobs:
           git --no-pager log -1 || true
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
 
       - name: Run vllm-ascend/tests/e2e/run_doctests.sh
         run: |

.github/workflows/vllm_ascend_test.yaml

@@ -81,15 +81,15 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [main]
+        vllm_version: [v0.10.1.1, main]
     steps:
       - name: Install packages
         run: |
           apt-get update -y
           apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
 
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           ref: ${{ matrix.vllm_version }}
@@ -102,7 +102,7 @@ jobs:
           python3 -m pip uninstall -y triton
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
 
       - name: Install vllm-project/vllm-ascend
         run: |
@@ -137,7 +137,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-1]
-        vllm_version: [main]
+        vllm_version: [v0.10.1.1, main]
     name: singlecard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -219,7 +219,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-2]
-        vllm_version: [main]
+        vllm_version: [v0.10.1.1, main]
     name: multicard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -278,7 +278,6 @@ jobs:
           # To avoid oom, we need to run the test in a single process.
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_dbo
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_alltoallv
           pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_Qwen3_W4A8DYNAMIC

.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: [main]
+        vllm_version: [v0.10.1.1, main]
     name: 310p e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -77,15 +77,15 @@ jobs:
           apt install git -y
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
 
       - name: Install system dependencies
         run: |
           apt-get -y install `cat packages.txt`
           apt-get -y install git vim wget net-tools gcc g++ cmake libnuma-dev curl gnupg2
 
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           ref: ${{ matrix.vllm_version }}

.github/workflows/vllm_ascend_test_pd.yaml

@@ -80,15 +80,15 @@ jobs:
           git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
 
       - name: Checkout vllm-project/vllm-ascend repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
 
       - name: Install system dependencies
         run: |
           apt-get -y install `cat packages.txt`
           apt-get -y install gcc g++ cmake libnuma-dev
 
       - name: Checkout vllm-project/vllm repo
-        uses: actions/checkout@v5
+        uses: actions/checkout@v4
         with:
           repository: vllm-project/vllm
           ref: ${{ matrix.vllm_verison }}

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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 
 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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 
 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=v0.10.0
+ARG VLLM_TAG=v0.10.1.1
 
 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.

tests/e2e/multicard/test_offline_inference_distributed.py

@@ -78,26 +78,6 @@ def test_models_distributed_DeepSeek_multistream_moe():
         vllm_model.generate_greedy(example_prompts, max_tokens)
 
 
-@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_DBO": "1"})
-def test_models_distributed_DeepSeek_dbo():
-    example_prompts = ["The president of the United States is"] * 41
-    dtype = "half"
-    sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
-    with VllmRunner(
-            "deepseek-ai/DeepSeek-V2-Lite",
-            dtype=dtype,
-            tensor_parallel_size=2,
-            distributed_executor_backend="mp",
-    ) as vllm_model:
-        model_arch = 'DeepseekV2ForCausalLM'
-        registed_models = ModelRegistry.models
-        assert registed_models[
-            model_arch].module_name == "vllm_ascend.models.deepseek_dbo"
-        assert registed_models[
-            model_arch].class_name == "CustomDeepseekDBOForCausalLM"
-        vllm_model.generate(example_prompts, sampling_params)
-
-
 @pytest.mark.skip(
     reason=
     "deepseek dbo dose not consider the support on half precision float, will enable this ut after we actually support it"