Update vllm pin to 12.24 (#5307)

### What this PR does / why we need it?
Fix vllm break in the pr:
1. [Add MiMo-V2-Flash support]
(https://github.com/vllm-project/vllm/pull/30836)

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

### How was this patch tested?

Co-authored-by: zxwang [1476209578@qq.com](mailto:1476209578@qq.com)

- vLLM version: release/v0.13.0
- vLLM main:
5fbfa8d9ef

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: zxwang <1476209578@qq.com>
Co-authored-by: zxwang <1476209578@qq.com>

.github/workflows/bot_pr_create.yaml

@@ -34,7 +34,7 @@ jobs:
     steps:
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=5fbfa8d9ef15948599631baeb91e8220b2ee9bcc
+          VLLM_COMMIT=bc0a5a0c089844b17cb93f3294348f411e523586
           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: [5fbfa8d9ef15948599631baeb91e8220b2ee9bcc, v0.13.0]
+        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, 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: 5fbfa8d9ef15948599631baeb91e8220b2ee9bcc
+      vllm: bc0a5a0c089844b17cb93f3294348f411e523586
   changes:
     runs-on: linux-aarch64-a2-0
     outputs:
@@ -90,7 +90,7 @@ jobs:
         SOC_VERSION: ascend910b1
     strategy:
       matrix:
-        vllm_version: [5fbfa8d9ef15948599631baeb91e8220b2ee9bcc, v0.13.0]
+        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0]
 
     steps:
       - name: Free up disk space
@@ -160,7 +160,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [5fbfa8d9ef15948599631baeb91e8220b2ee9bcc, v0.13.0]
+        vllm_version: [bc0a5a0c089844b17cb93f3294348f411e523586, 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    | 5fbfa8d9ef15948599631baeb91e8220b2ee9bcc, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
+|     main    | bc0a5a0c089844b17cb93f3294348f411e523586, v0.13.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
 
 ## Release cadence
 

vllm_ascend/ops/linear.py

@@ -109,7 +109,9 @@ class AscendQKVParallelLinear(QKVParallelLinear):
         *,
         return_bias: bool = True,
         disable_tp: bool = False,
+        v_head_size: int | None = None,
     ):
+        self.v_head_size = v_head_size if v_head_size is not None else head_size
         self.custom_op, _, tp_size = get_parallel_op(disable_tp, prefix, self,
                                                      "column")
         # TODO(realliujiaxu): Replace the initialization code below with super().__init__ after linear of vllm supports custom comm group