squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Misc] Fix typo in scheduler.py (#4022)

Browse Source
This commit is contained in:
Zhuohan Li 2024-04-12 13:56:04 -07:00 committed by GitHub
parent 96b6a6d790
commit d4ec9ffb95
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/core/scheduler.py
View File

@ -674,7 +674,7 @@ class Scheduler:
def _schedule_default(self) -> SchedulerOutputs: def _schedule_default(self) -> SchedulerOutputs:
"""Schedule queued requests. """Schedule queued requests.
The current policy is designed to opimimize the throughput. First, The current policy is designed to optimize the throughput. First,
it batches as many prefill requests as possible. And it schedules it batches as many prefill requests as possible. And it schedules
decodes. If there's a pressure on GPU memory, decode requests can decodes. If there's a pressure on GPU memory, decode requests can
be swapped or preempted. be swapped or preempted.