Skip to content
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.

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

Fix (gpxq): tensor unpacking and Cholesky stabilization #1111

Merged
merged 2 commits into from
Dec 5, 2024

Conversation

i-colbert
Copy link
Collaborator

@i-colbert i-colbert commented Dec 4, 2024

Reason for this PR

Stabilizing Cholesky decomposition in GPTQ and generalizing the quant tensor unpacking to work with other quant tensors.

Changes Made in this PR

  • Centralized quant tensor unpacking in GPxQ base class and generalized to use cache_class attribute of input_quant
  • Added another input to GPTQ.single_layer_update(...) to stabilize the Cholesky decomposition of the inverse Hessian

Testing Summary

N/A

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.

@Giuseppe5 Giuseppe5 self-requested a review December 5, 2024 02:21
@Giuseppe5 Giuseppe5 merged commit 2a1b14f into Xilinx:dev Dec 5, 2024
381 of 396 checks passed
@i-colbert i-colbert deleted the minor-gptq-fixes branch December 5, 2024 15:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants