apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix scheduler bug due to async running (#3293)

Browse Source
This commit is contained in:
chenjian
2025-08-10 13:54:59 +08:00
committed by GitHub
parent c208086f61
commit a84a98b107
2 changed files with 28 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fastdeploy/output/token_processor.py
View File

@@ -432,6 +432,11 @@ class TokenProcessor:
tokens = tokens[2 : batch + 2]
batch_result = list()
if envs.ENABLE_V1_KVCACHE_SCHEDULER:
need_to_be_reschedule_req_ids = list(self.resource_manager.to_be_rescheduled_request_id_set)
for request_id in need_to_be_reschedule_req_ids:
if self.resource_manager.requests[request_id].idx >= (batch - 1): # No more token generated for preempted request
self.resource_manager.reschedule_preempt_task(request_id)
for i in range(batch):
if self.resource_manager.stop_flags[i]:
continue
@@ -458,6 +463,8 @@ class TokenProcessor:
if recovery_stop:
llm_logger.info(f"recovery stop signal found at task {task_id}")
if not recovery_stop and token_id < 0:
if task_id in self.resource_manager.to_be_rescheduled_request_id_set:
self.resource_manager.reschedule_preempt_task(task_id)
continue
if task.get("prefill_chunk_info", None) is not None: