Skip to content

optimize: improve scheduler policy lookup performance #22573

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

optimize: improve scheduler policy lookup performance #22573

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6875945
optimize: improve scheduler policy lookup performance
skyloevil Aug 9, 2025
049cf28
refactor: optimize scheduler policy lookup with try/except pattern
skyloevil Aug 9, 2025
8d5cd75
pre-commit solved
skyloevil Aug 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions vllm/v1/core/sched/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,11 @@


class Scheduler(SchedulerInterface):
# Policy mapping for efficient policy lookup
_POLICY_MAPPING = {
"priority": SchedulingPolicy.PRIORITY,
"fcfs": SchedulingPolicy.FCFS,
}

def __init__(
self,
Expand Down Expand Up @@ -99,13 +104,12 @@ def __init__(
# req_id -> Request
self.requests: dict[str, Request] = {}
# Scheduling policy
if self.scheduler_config.policy == "priority":
self.policy = SchedulingPolicy.PRIORITY
elif self.scheduler_config.policy == "fcfs":
self.policy = SchedulingPolicy.FCFS
else:
policy_name = self.scheduler_config.policy
try:
self.policy = self._POLICY_MAPPING[policy_name]
except KeyError:
raise ValueError(
f"Unknown scheduling policy: {self.scheduler_config.policy}")
f"Unknown scheduling policy: {policy_name}") from None
# Priority queues for requests.
self.waiting = create_request_queue(self.policy)
self.running: list[Request] = []
Expand Down