Skip to content

[DRAFT][DO NOT REVIEW] Compile once per block #25792

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

Jump to bottom
Draft
wants to merge 12 commits into
base: main
Choose a base branch
from
Draft

[DRAFT][DO NOT REVIEW] Compile once per block #25792

wants to merge 12 commits into from
+167 −89

Conversation

Lucaskabela
Copy link
Contributor

@Lucaskabela Lucaskabela commented Sep 26, 2025 •
edited by github-actions bot
Loading

Please do not review - checking signals

Purpose

Test Plan

Test Result

Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

@Lucaskabela
Support compile on any module (towards compilable vision transformer)
c2fbae6 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Changes for benchmarking
9d0ba7c 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Minimize to just qwen2_5 again for consistency
6179540 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Update dep
4da6ee0 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Working version
444b43d 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Working version2
9e7e8b6 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Tidy changes to qwen
3b043ce 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Rebase and tidy
1acab33 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Rebase on main, more benchmarking
48f4e2b 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Mark seqlen dynamic too
f304bb5 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
Remove errenously added import
bbe5af6 
Signed-off-by: Lucas Kabela <[email protected]>
@Lucaskabela
See title; consolidate so that we only compile a class once
a8a1e83 
Signed-off-by: Lucas Kabela <[email protected]>
@mergify mergify bot added the qwen Related to Qwen models label Sep 26, 2025
@Lucaskabela Lucaskabela force-pushed the lucaskabela/compile_once_per_block branch from 0364a68 to a8a1e83 Compare September 26, 2025 23:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@sighingnow sighingnow Awaiting requested review from sighingnow sighingnow will be requested when the pull request is marked ready for review sighingnow is a code owner

@zou3519 zou3519 Awaiting requested review from zou3519 zou3519 will be requested when the pull request is marked ready for review zou3519 is a code owner

@youkaichao youkaichao Awaiting requested review from youkaichao youkaichao will be requested when the pull request is marked ready for review youkaichao is a code owner

@ProExpertProg ProExpertProg Awaiting requested review from ProExpertProg ProExpertProg will be requested when the pull request is marked ready for review ProExpertProg is a code owner

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
qwen Related to Qwen models
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@Lucaskabela