[bugfix] fix type[AttentionBackend] bug in kv_connector_base_v1 (#30051)

Signed-off-by: 01267596 <xiongkai123@cmbchina.com>
Co-authored-by: 01267596 <xiongkai123@cmbchina.com>

vllm/distributed/kv_transfer/kv_connector/v1/base.py

@@ -239,7 +239,7 @@ class KVConnectorBase_V1(ABC):
         return
 
     def register_cross_layers_kv_cache(
-        self, kv_cache: torch.Tensor, attn_backend: type[AttentionBackend]
+        self, kv_cache: torch.Tensor, attn_backend: type["AttentionBackend"]
     ):
         """
         Initialize with a single KV cache tensor used by all layers.