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, 00:15 UTC
[Doc] Correct comment for _jobs dict in OffloadingConnectorWorker (#32556)
Deming committed
Jan 19, 2026 at 04:46 UTC
5480c6b1fa36271171903476f4dcb057c45c49ea
1 file changed
+1
-1
vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
+1
-1
@@ -434,7 +434,7 @@ class OffloadingConnectorWorker:
434
435
self._job_counter = 0
436
437
- # req_id -> (job_id, store)
437
+ # job_id -> (req_id, store)
438
self._jobs: dict[int, tuple[ReqId, bool]] = {}
439
# req_id -> active job IDs
440
self._load_job: dict[ReqId, int] = {}