EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[UCMConnector]Add has_connector_metadata (#6172)

Browse Source 
### What this PR does / why we need it?
ucm_connector add has `has_connector_metadata` interface to adapt to the
latest KV connector in vLLM.

### Does this PR introduce _any_ user-facing change?
this PR doesn't introduce _any_ user-facing change.


### How was this patch tested?

- vLLM version: v0.14.0
- vLLM main:
d68209402d

Signed-off-by: UnifiedCacheManager <unifiedcachem@163.com>
This commit is contained in:
UnifiedCacheManager
2026-01-23 21:16:48 +08:00
committed by GitHub
parent 717d299ae5
commit a2f022f9b6
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/distributed/kv_transfer/kv_pool/ucm_connector.py
View File

@@ -43,6 +43,14 @@ class UCMConnectorV1(KVConnectorBase_V1):
# ============================== # ==============================
# Worker-side methods # Worker-side methods
# ============================== # ==============================
def has_connector_metadata(self) -> bool:
"""Check whether the connector metadata is currently set.
Returns:
bool: True if connector metadata exists, False otherwise.
"""
return self._ucm_engine.has_connector_metadata()
def register_kv_caches(self, kv_caches: dict[str, torch.Tensor]) -> None: def register_kv_caches(self, kv_caches: dict[str, torch.Tensor]) -> None:
""" """
Initialize with the KV caches. Useful for pre-registering the Initialize with the KV caches. Useful for pre-registering the