Skip to content

[WIP] scheduler exploration sort based on abs tkv difference #971

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

Draft
yannicks1 wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[WIP] scheduler exploration sort based on abs tkv difference #971

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 7 additions & 0 deletions sendnn_inference/v1/core/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,13 @@ def schedule(self) -> "SchedulerOutput":
while self.skipped_waiting:
holdback_queue.append(self.skipped_waiting.pop_request())

# Greedily pick the request whose prompt length is closest to the
# current batch TKV so the incoming sequence aligns with the running
# decode batch as tightly as possible. May starve outliers — intentional.
holdback_queue = deque(
sorted(holdback_queue, key=lambda r: abs(r.num_prompt_tokens - self.tkv))
)

# Check if new requests can be scheduled for prefill
while holdback_queue:
if self.can_schedule_prefill(holdback_queue[0]):
Expand Down
Loading