Skip to content

Feat (brevitas_examples/sdxl): better GPTQ #1250

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
Merged
merged 7 commits into from
May 6, 2025
Merged

Feat (brevitas_examples/sdxl): better GPTQ #1250

merged 7 commits into from
May 6, 2025

Conversation

Giuseppe5
Copy link
Collaborator

Reason for this PR

Few shot calibration + GPTQ

Some details need refining

Changes Made in this PR

Testing Summary

Risk Highlight

  • This PR includes code from another work (please detail).
  • This PR contains API-breaking changes.
  • This PR depends on work in another PR (please provide links/details).
  • This PR introduces new dependencies (please detail).
  • There are coverage gaps not covered by tests.
  • Documentation updates required in subsequent PR.

Checklist

  • Code comments added to any hard-to-understand areas, if applicable.
  • Changes generate no new warnings.
  • Updated any relevant tests, if applicable.
  • No conflicts with destination dev branch.
  • I reviewed my own code changes.
  • Initial CI/CD passing.
  • 1+ reviews given, and any review issues addressed and approved.
  • Post-review full CI/CD passing.

@nickfraser nickfraser added enhancement New feature or request next release PRs which should be merged for the next release labels Apr 11, 2025
@Giuseppe5 Giuseppe5 marked this pull request as ready for review April 14, 2025 08:30
Giuseppe5
Giuseppe5 commented Apr 14, 2025
View reviewed changes
src/brevitas/graph/gptq.py
(self.groups, self.columns, self.columns),
device='cpu',
dtype=torch.float32,
)
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe I should re-introduce this but I was getting weird CUDA errors. Also, since we are storing in CPU, not sure why we need to use pin_memory.
@i-colbert maybe you can comment before we merge

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

From what I can remember, it was used to improve data transfer speeds from GPU to CPU, which is why it is only enabled if a GPU is available.

nickfraser
nickfraser approved these changes Apr 25, 2025
View reviewed changes
Copy link
Collaborator

@nickfraser nickfraser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

A few comments / question, but in principle, approved.

@Giuseppe5 Giuseppe5 requested a review from nickfraser May 5, 2025 18:23
nickfraser
nickfraser approved these changes May 6, 2025
View reviewed changes
Copy link
Collaborator

@nickfraser nickfraser left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@Giuseppe5 Giuseppe5 merged commit e578918 into Xilinx:dev May 6, 2025
374 of 396 checks passed
@Giuseppe5 Giuseppe5 deleted the faster_sdxl branch May 6, 2025 11:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@i-colbert i-colbert i-colbert left review comments

@nickfraser nickfraser nickfraser approved these changes

Assignees
No one assigned
Labels
enhancement New feature or request next release PRs which should be merged for the next release
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@Giuseppe5 @nickfraser @i-colbert