Update corresponding vllm commit ID to 12 29 (#5475)

### What this PR does / why we need it?
- Fixes vllm break:
1. [[BugFix] register quant scale tensors as buffer #31395]
(https://github.com/vllm-project/vllm/pull/31395)

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
5326c89803

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>

.github/workflows/bot_pr_create.yaml

@@ -34,7 +34,7 @@ jobs:
     steps:
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=5326c89803566a131c928f7fdd2100b75c981a42
+          VLLM_COMMIT=45c1ca1ca1ee8fa06df263c8715e8a412ff408d4
           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: [5326c89803566a131c928f7fdd2100b75c981a42, v0.13.0]
+        vllm_version: [45c1ca1ca1ee8fa06df263c8715e8a412ff408d4, 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: 5326c89803566a131c928f7fdd2100b75c981a42
+      vllm: 45c1ca1ca1ee8fa06df263c8715e8a412ff408d4
   changes:
     runs-on: linux-aarch64-a2-0
     outputs:
@@ -90,7 +90,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [5326c89803566a131c928f7fdd2100b75c981a42, v0.13.0]
+        vllm_version: [45c1ca1ca1ee8fa06df263c8715e8a412ff408d4, v0.13.0]
 
     steps:
       - name: Free up disk space
@@ -160,7 +160,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [5326c89803566a131c928f7fdd2100b75c981a42, v0.13.0]
+        vllm_version: [45c1ca1ca1ee8fa06df263c8715e8a412ff408d4, 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

@@ -51,7 +51,7 @@ 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    | 5326c89803566a131c928f7fdd2100b75c981a42, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
+|     main    | 45c1ca1ca1ee8fa06df263c8715e8a412ff408d4, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
 
 ## Release cadence
 

vllm_ascend/worker/worker.py

@@ -27,7 +27,7 @@ import torch_npu
 import vllm.envs as envs_vllm
 from torch_npu.op_plugin.atb._atb_ops import _register_atb_extensions
 from torch_npu.profiler import dynamic_profile as dp
-from vllm.config import VllmConfig
+from vllm.config import VllmConfig, set_current_vllm_config
 from vllm.distributed import (ensure_model_parallel_initialized,
                               init_distributed_environment)
 from vllm.distributed.ec_transfer import ensure_ec_transfer_initialized
@@ -351,7 +351,8 @@ class NPUWorker(WorkerBase):
         else:
             from contextlib import nullcontext
             context = nullcontext()  # type: ignore
-        with context:
+
+        with context, set_current_vllm_config(self.vllm_config):
             self.model_runner.load_model()
 
     def compile_or_warm_up_model(self) -> None: