apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix mtp reschedule (#5165)

Browse Source
This commit is contained in:
GoldPancake
2025-11-21 19:31:35 +08:00
committed by GitHub
parent 3ea1b44a58
commit ab3a2e45ff
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
fastdeploy/output/token_processor.py
View File

@@ -622,11 +622,11 @@ class TokenProcessor:
+ i * MAX_DRAFT_TOKENS
+ accept_num[i]
].tolist()
if (not recovery_stop) and (len(token_ids) == 0 or token_ids[-1] <= 0):
if envs.ENABLE_V1_KVCACHE_SCHEDULER:
if task_id in self.resource_manager.to_be_rescheduled_request_id_set:
self.resource_manager.reschedule_preempt_task(task_id)
continue
if (not recovery_stop) and (len(token_ids) == 0 or token_ids[-1] <= 0):
if envs.ENABLE_V1_KVCACHE_SCHEDULER:
if task_id in self.resource_manager.to_be_rescheduled_request_id_set:
self.resource_manager.reschedule_preempt_task(task_id)
continue
else:
token_id = int(tokens[i, 0])
token_ids = [token_id]