[BugFix][v0.18.0] require piecewise cudagraph for layerwise AscendSto… (#8282)

<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
ref:https://github.com/vllm-project/vllm-ascend/issues/8184
following https://github.com/vllm-project/vllm/pull/31057, add
`requires_piecewise_for_cudagraph` for `AscendStoreConnector`

### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->

Signed-off-by: Pz1116 <zpbzpb123123@gmail.com>

vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/ascend_store_connector.py

@@ -64,6 +64,16 @@ class AscendStoreKVEvents(KVConnectorKVEvents):
 
 
 class AscendStoreConnector(KVConnectorBase_V1):
+    @classmethod
+    def requires_piecewise_for_cudagraph(cls, extra_config: dict[str, Any]) -> bool:
+        """
+        AscendStore requires PIECEWISE CUDA graph mode when layerwise
+        operations are enabled. The layerwise load/save hooks perform
+        async synchronization that cannot be safely captured in CUDA
+        graphs.
+        """
+        return extra_config.get("use_layerwise", False)
+
     def __init__(self, vllm_config: VllmConfig, role: KVConnectorRole, kv_cache_config: KVCacheConfig | None = None):
         super().__init__(vllm_config=vllm_config, role=role, kv_cache_config=kv_cache_config)
         self.kv_role = vllm_config.kv_transfer_config.kv_role