change commit id to 0.11.1

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

Author: wxsIcey

.github/workflows/format_pr_body.yaml

@@ -36,7 +36,7 @@ jobs:
 
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=83f478bb19489b41e9d208b47b4bb5a95ac171ac
+          VLLM_COMMIT=releases/v0.11.1
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository

.github/workflows/vllm_ascend_test.yaml

@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/pre-commit.yml
     with:
-      vllm: 83f478bb19489b41e9d208b47b4bb5a95ac171ac
+      vllm: releases/v0.11.1
 
   changes:
     runs-on: ubuntu-latest
@@ -83,7 +83,7 @@ jobs:
         VLLM_USE_MODELSCOPE: True
     strategy:
       matrix:
-        vllm_version: [83f478bb19489b41e9d208b47b4bb5a95ac171ac, v0.11.0]
+        vllm_version: [releases/v0.11.1, v0.11.0]
     steps:
       - name: Install packages
         run: |
@@ -140,7 +140,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [83f478bb19489b41e9d208b47b4bb5a95ac171ac, v0.11.0]
+        vllm_version: [releases/v0.11.1, 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_full.yaml

@@ -69,7 +69,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [83f478bb19489b41e9d208b47b4bb5a95ac171ac, v0.11.0]
+        vllm_version: [releases/v0.11.1, v0.11.0]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml

tests/e2e/singlecard/test_embedding_aclgraph.py

@@ -24,10 +24,10 @@
 from tests.e2e.utils import check_embeddings_close
 
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
-os.environ["VLLM_USE_MODELSCOPE"] = "True"
 
 MODELS = ["BAAI/bge-m3"]
 
+
 @pytest.mark.parametrize("model_name", MODELS)
 def test_aclgrpah_embed_models_correctness(model_name):
     queries = ['What is the capital of China?', 'Explain gravity']
@@ -36,14 +36,12 @@ def test_aclgrpah_embed_models_correctness(model_name):
             model_name,
             task="embed",
             enforce_eager=False,
-            # load_format="dummy",
     ) as vllm_aclgraph_runner:
         vllm_aclgraph_outputs = vllm_aclgraph_runner.encode(queries)
 
     with VllmRunner(
             model_name,
             task="embed",
-            # load_format="dummy",
             enforce_eager=True,
     ) as vllm_runner:
         vllm_outputs = vllm_runner.encode(queries)