test 092rc1

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>

Author: Yikun

.github/workflows/accuracy_test.yaml

@@ -37,7 +37,7 @@ on:
         # Current supported vLLM versions
         options:
           - main
-          - v0.9.1
+          - v0.9.2rc1
           - v0.7.3
       vllm-ascend-version:
         description: 'vllm-ascend version:'
@@ -163,7 +163,7 @@ jobs:
           repository: vllm-project/vllm
           path: ./vllm-empty
           # Please also update this when bump matched version
-          ref: ${{ github.event.inputs.vllm-version || 'v0.9.1' }}
+          ref: ${{ github.event.inputs.vllm-version || 'v0.9.2rc1' }}
 
       - name: Install vllm-project/vllm from source
         working-directory: ./vllm-empty

.github/workflows/nightly_benchmarks.yaml

@@ -50,7 +50,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: v0.9.1
+          - vllm_branch: v0.9.2rc1
             vllm_ascend_branch: main
             vllm_use_v1: 1
       max-parallel: 1

.github/workflows/vllm_ascend_test.yaml

@@ -132,10 +132,10 @@ jobs:
           tools/mypy.sh 1 ${{ matrix.python-version }}
 
   ut:
-    needs: [lint]
+    # needs: [lint]
     name: unit test
     # only trigger e2e test on [pull request after lint passed] and [merged commit]
-    if: ${{ needs.lint.result == 'success' || github.event_name == 'push' }}
+    # if: ${{ needs.lint.result == 'success' || github.event_name == 'push' }}
     runs-on: ubuntu-latest
     container:
       image: m.daocloud.io/quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
@@ -144,7 +144,7 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [main, v0.9.1]
+        vllm_version: [main, v0.9.2rc1]
     steps:
       - name: Install packages
         run: |
@@ -201,7 +201,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-arm64-npu-1]
-        vllm_version: [main, v0.9.1]
+        vllm_version: [main, v0.9.2rc1]
     name: singlecard e2e test
     runs-on: ${{ matrix.os }}
     container:
@@ -302,7 +302,7 @@ jobs:
       max-parallel: 1
       matrix:
         os: [linux-arm64-npu-4]
-        vllm_version: [main, v0.9.1]
+        vllm_version: [main, v0.9.2rc1]
     name: multicard e2e test
     runs-on: ${{ matrix.os }}
     container:

.github/workflows/vllm_ascend_test_long_term.yaml

@@ -43,7 +43,7 @@ jobs:
       max-parallel: 2
       matrix:
         os: [linux-arm64-npu-1, linux-arm64-npu-4]
-        vllm_version: [main, v0.9.1]
+        vllm_version: [main, v0.9.2rc1]
     name: vLLM Ascend long term test
     runs-on: ${{ matrix.os }}
     container:

.github/workflows/vllm_ascend_test_pd.yaml

@@ -44,7 +44,7 @@ jobs:
         vllm_verison: [
             # revert me when V1 disaggregation prefill is merged in main
             # main, 
-            v0.9.1
+            v0.9.2rc1
           ]
     name: vLLM Ascend prefilling decoding disaggregation test
     runs-on: linux-arm64-npu-static-8

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=v0.9.1
+ARG VLLM_TAG=v0.9.2rc1
 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=v0.9.1
+ARG VLLM_TAG=v0.9.2rc1
 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=v0.9.1
+ARG VLLM_TAG=v0.9.2rc1
 
 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=v0.9.1
+ARG VLLM_TAG=v0.9.2rc1
 
 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.

docs/source/conf.py

@@ -65,15 +65,15 @@
     # the branch of vllm, used in vllm clone
     # - main branch: 'main'
     # - vX.Y.Z branch: 'vX.Y.Z'
-    'vllm_version': 'v0.9.1',
+    'vllm_version': 'v0.9.2rc1',
     # the branch of vllm-ascend, used in vllm-ascend clone and image tag
     # - main branch: 'main'
     # - vX.Y.Z branch: latest vllm-ascend release tag
     'vllm_ascend_version': 'v0.9.1rc1',
     # the newest release version of vllm-ascend and matched vLLM, used in pip install.
     # This value should be updated when cut down release.
     'pip_vllm_ascend_version': "0.9.1rc1",
-    'pip_vllm_version': "0.9.1",
+    'pip_vllm_version': "0.9.2",
     # CANN image tag
     'cann_image_tag': "8.1.rc1-910b-ubuntu22.04-py3.10",
 }