Support prefill max requests limitation (#14993)
This commit is contained in:
@@ -1822,6 +1822,7 @@ class Scheduler(
|
||||
chunked_prefill_size,
|
||||
running_bs if self.is_mixed_chunk else 0,
|
||||
self.priority_scheduling_preemption_threshold,
|
||||
prefill_max_requests=self.server_args.prefill_max_requests,
|
||||
)
|
||||
|
||||
if self.chunked_req is not None:
|
||||
|
||||
Reference in New Issue
Block a user