[feature]Pooling Features and PCP Adaptation (#4143)

This PR let pooling kv connector support pcp feature

- vLLM version: v0.11.2

---------

Signed-off-by: fjw <2270923832@qq.com>
Signed-off-by: SlightwindSec <slightwindsec@gmail.com>
Co-authored-by: SlightwindSec <slightwindsec@gmail.com>

vllm_ascend/distributed/kvpool/ascend_store_connector.py

@@ -43,8 +43,6 @@ class AscendStoreConnector(KVConnectorBase_V1):
 
         self.kv_caches: dict[str, torch.Tensor] = {}
 
-        self._block_size = vllm_config.cache_config.block_size
-
         self.sended_but_unfinished_reqs: set[str] = set()
 
         if role == KVConnectorRole.SCHEDULER: