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 12, 17:15 UTC
[chore][LMCache connector] Remove useless logs from lmcache connector (#29069)
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Yihua Cheng committed
Nov 21, 2025 at 19:18 UTC
77e1c035d039ec546bb01b4915eed6b5735156c2
2 files changed
-4
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py
-1
@@ -310,7 +310,6 @@ class LMCacheMPWorkerAdapter:
310
request_id,
311
result,
312
)
313
- logger.info("Retrieve request for request_id=%s finished", request_id)
313
314
# Remove the finished requests from the tracking dicts
315
for request_id in finished_stores:
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py
-3
@@ -469,9 +469,6 @@ class LMCacheMPConnector(KVConnectorBase_V1):
469
ops.append(meta.op)
470
471
if len(request_ids) > 0:
472
- logger.info(
473
- "HERE! SUBMITTING THE BATCHED RETRIEVE REQUESTS %s", request_ids
474
- )
472
self.worker_adapter.batched_submit_retrieve_requests(
473
request_ids, ops, event
474
)