[Qwen-moe] Remove the minor operation arange

Signed-off-by: s30076806 <[email protected]>

Author: s-jiayang

.github/ISSUE_TEMPLATE/750-RFC.yml

@@ -40,7 +40,7 @@ body:
   attributes:
     label: Any Other Things.
     description: >
-      Any other things you would like to mention.
+      Any other things you would like to mention, such as feature branch request.
   validations:
     required: false
 - type: markdown

.github/workflows/format_pr_body.yaml

@@ -46,7 +46,7 @@ jobs:
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository
-        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
       - name: Set up Python
         uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0

.github/workflows/release_code.yml

@@ -43,7 +43,7 @@ jobs:
       matrix:
         python-version: ["3.11"]
     steps:
-      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
       - name: Print
         run: |

.github/workflows/release_whl.yml

@@ -52,7 +52,7 @@ jobs:
          ) }}
     runs-on: ${{ matrix.os }}
     steps:
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+    - uses: actions/checkout@ff7abcd0c3c05ccf6adc123a8cd1fd4fb30fb493 # v4.2.2
 
     - name: Print
       run: |

.github/workflows/vllm_ascend_test.yaml

@@ -81,7 +81,7 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [main, v0.10.0]
+        vllm_version: [v0.10.1.1, main]
     steps:
       - name: Install packages
         run: |
@@ -137,7 +137,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-1]
-        vllm_version: [main, v0.10.0]
+        vllm_version: [v0.10.1.1, main]
     name: singlecard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -185,17 +185,14 @@ jobs:
         run: |
           pip install -r requirements-dev.txt
           pip install -v -e .
-          if [[ "${{ matrix.vllm_version }}" == "v0.10.0" ]]; then
-            pip install "transformers<4.54.0"
-          fi
 
       - name: Run e2e test
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
           pytest -sv tests/e2e/singlecard/test_offline_inference.py
-          pytest -sv tests/e2e/singlecard/test_ilama_lora.py
+          # pytest -sv tests/e2e/singlecard/test_ilama_lora.py
           pytest -sv tests/e2e/singlecard/test_guided_decoding.py
           pytest -sv tests/e2e/singlecard/test_camem.py
           pytest -sv tests/e2e/singlecard/test_embedding.py
@@ -222,7 +219,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-aarch64-a2-2]
-        vllm_version: [main, v0.10.0]
+        vllm_version: [v0.10.1.1, main]
     name: multicard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -270,21 +267,17 @@ jobs:
         run: |
           pip install -r requirements-dev.txt
           pip install -v -e .
-          if [[ "${{ matrix.vllm_version }}" == "v0.10.0" ]]; then
-            pip install "transformers<4.54.0"
-          fi
 
       - name: Run vllm-project/vllm-ascend test
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
-          pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py
+          # pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py
           # Fixme: run VLLM_USE_MODELSCOPE=True pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py will raise error.
           # 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, v0.10.0]
+        vllm_version: [v0.10.1.1, main]
     name: 310p e2e test
     runs-on: ${{ matrix.os }}
     container:

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/ && \