upgrade vLLM to 0.12.0 tag (#4647)

Upgrade vLLM to v0.12.0 tag

- vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
- vLLM main:
86e178f7c4

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

.github/workflows/vllm_ascend_test_pr_light.yaml

@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/pre-commit.yml
     with:
-      vllm: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
+      vllm: v0.12.0
   changes:
     runs-on: ubuntu-latest
     outputs:
@@ -84,7 +84,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
+        vllm_version: [v0.12.0]
         
     steps:
       - name: Free up disk space
@@ -137,7 +137,8 @@ jobs:
             --ignore tests/ut/torchair/models/test_torchair_deepseek_v2.py \
             --ignore tests/ut/models/test_qwen2_vl.py \
             --ignore tests/ut/models/test_qwen2_5_vl.py \
-            --ignore tests/ut/models/test_qwen2_5_vl_without_padding.py
+            --ignore tests/ut/models/test_qwen2_5_vl_without_padding.py \
+            --ignore tests/ut/model_loder
 
       - name: Upload coverage to Codecov
         # only upload coverage when commits merged
@@ -154,7 +155,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24]
+        vllm_version: [v0.12.0]
     # 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.