mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00
fix scheduler bug in release2.1 (#3295)
This commit is contained in:
@@ -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:
|
||||
|
Reference in New Issue
Block a user