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 10, 05:15 UTC
[BugFix] [KVConnector] Fix KV events for LMCache connector (#32169)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Martin Hickey committed
Jan 13, 2026 at 15:50 UTC
510265472cb216daf7d8e83db6fa03ce48b0f5fc
1 file changed
+1
-1
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py
+1
-1
@@ -234,7 +234,7 @@ class LMCacheConnectorV1(KVConnectorBase_V1):
234
lora_id=e.lora_id,
235
block_size=e.block_size,
236
medium=e.medium,
237
- lora_name=e.lora_name,
237
+ lora_name=getattr(e, "lora_name", None),
238
)
239
for e in events
240
]