A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[BUGFIX][NIXL] quick fix for 'assert self.connector_worker is not None' in get_kv_connector_stats (#26851)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Chendi.Xue committed
Oct 14, 2025 at 21:33 UTC
bfad142e257be6699868f7816ca64c408bc32916
1 file changed
+2
-1
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
+2
-1
@@ -241,7 +241,8 @@ class NixlConnector(KVConnectorBase_V1):
241
return self.connector_worker.get_block_ids_with_load_errors()
242
243
def get_kv_connector_stats(self) -> KVConnectorStats | None:
244
- assert self.connector_worker is not None
244
+ if self.connector_worker is None:
245
+ return None
246
return self.connector_worker.get_kv_connector_stats()
247
248
@classmethod