xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 21:55:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

OffloadingConnector: Fix GPU block tracking bug (#25856)

Browse Source 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
This commit is contained in:
Or Ozeri 2025-09-30 22:53:04 +03:00 committed by GitHub
parent fb610ae684
commit cfd302db9b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
View File

@ -278,8 +278,9 @@ class OffloadingConnectorScheduler:
req, start_idx=start_block_idx, end_idx=num_blocks)
store_output = self.manager.prepare_store(new_block_hashes)
if store_output is None:
logger.warning("Cannot store %s blocks", num_new_blocks)
break
logger.warning("Request %s: cannot store %s blocks", req_id,
num_new_blocks)
continue
self._next_stored_block_idx[req_id] = num_blocks