Update vllm pin to 12.25 (#5342)

### What this PR does / why we need it?
- Fix vllm break in the pr:
1.[Drop v0.14 deprecations
]https://github.com/vllm-project/vllm/pull/31285
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

---------

Signed-off-by: ZT-AIA <1028681969@qq.com>

.github/workflows/bot_pr_create.yaml

@@ -34,7 +34,7 @@ jobs:
     steps:
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=bc0a5a0c089844b17cb93f3294348f411e523586
+          VLLM_COMMIT=254f6b986720c92ddf97fbb1a6a6465da8e87e29
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> $GITHUB_ENV
 
       - name: Checkout repository

.github/workflows/pr_test_full.yaml

@@ -74,7 +74,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0]
+        vllm_version: [254f6b986720c92ddf97fbb1a6a6465da8e87e29, v0.13.0]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml

.github/workflows/pr_test_light.yaml

@@ -42,7 +42,7 @@ jobs:
   lint:
     uses: ./.github/workflows/_pre_commit.yml
     with:
-      vllm: bc0a5a0c089844b17cb93f3294348f411e523586
+      vllm: 254f6b986720c92ddf97fbb1a6a6465da8e87e29
   changes:
     runs-on: linux-aarch64-a2-0
     outputs:
@@ -90,7 +90,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0]
+        vllm_version: [254f6b986720c92ddf97fbb1a6a6465da8e87e29, v0.13.0]
 
     steps:
       - name: Free up disk space
@@ -160,7 +160,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0]
+        vllm_version: [254f6b986720c92ddf97fbb1a6a6465da8e87e29, v0.13.0]
     # 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.

docs/source/community/versioning_policy.md

@@ -50,7 +50,7 @@ If you're using v0.7.3, don't forget to install [mindie-turbo](https://pypi.org/
 For main branch of vLLM Ascend, we usually make it compatible with the latest vLLM release and a newer commit hash of vLLM. Please note that this table is usually updated. Please check it regularly.
 | vLLM Ascend | vLLM         | Python           | Stable CANN | PyTorch/torch_npu  |
 |-------------|--------------|------------------|-------------|--------------------|
-|     main    | bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
+|     main    | 254f6b986720c92ddf97fbb1a6a6465da8e87e29, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
 
 ## Release cadence
 

tests/e2e/multicard/test_qwen3_moe.py

@@ -28,7 +28,7 @@ from unittest.mock import patch
 import openai
 import pytest
 from modelscope import snapshot_download  # type: ignore
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer, VllmRunner
 

tests/e2e/nightly/features/test_mtpx_deepseek_r1_0528_w8a8.py

@@ -19,7 +19,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/features/test_prefix_cache_deepseek_r1_0528_w8a8.py

@@ -17,7 +17,7 @@
 import json
 
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import get_TTFT, run_aisbench_cases

tests/e2e/nightly/features/test_prefix_cache_qwen3_32b_int8.py

@@ -17,7 +17,7 @@
 import json
 
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import get_TTFT, run_aisbench_cases

tests/e2e/nightly/features/test_qwen3_32b_int8_a3_feature_stack3.py

@@ -16,7 +16,7 @@
 #
 
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8.py

@@ -19,7 +19,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8_eplb.py

@@ -19,7 +19,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_deepseek_v3_2_exp_w8a8.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_glm4_5.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen2_5_vl_32b.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen2_5_vl_7b.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen3_235b_a22b_w8a8_eplb.py

@@ -19,7 +19,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen3_235b_w8a8.py

@@ -19,7 +19,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen3_30b_w8a8.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwen3_32b_int8.py

@@ -20,7 +20,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases

tests/e2e/nightly/models/test_qwq_32b.py

@@ -18,7 +18,7 @@ from typing import Any
 
 import openai
 import pytest
-from vllm.utils import get_open_port
+from vllm.utils.network_utils import get_open_port
 
 from tests.e2e.conftest import RemoteOpenAIServer
 from tools.aisbench import run_aisbench_cases