Skip to content

Implementing support for Non-Standard LoRA Format #7985

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

Merged
merged 10 commits into from
May 5, 2025

Conversation

hipsterusername
Copy link
Member

Summary

Bringing 7954 into separate PR for review/testing and finalization.

QA Instructions

Tested:
✅ Base Dev + Standard LoRA
✅ Base Dev + Non-Standard LoRA
✅ Quantized Dev + Standard LoRA
✅ Quantized Dev + Non-Standard LoRA

Merge Plan

Additional testing/review warranted to evaluate whether this non-standard format will conflict with other open Flux PRs (e.g., ACE++)

Checklist

  • The PR has a short but descriptive title, suitable for a changelog
  • Tests added / updated (if applicable)
  • Documentation added / updated (if applicable)
  • Updated What's New copy (if doing a release after this PR)

@github-actions github-actions bot added python PRs that change python files backend PRs that change backend files labels May 2, 2025
@hipsterusername hipsterusername force-pushed the training-model-loading-updates branch from 66448f6 to dc10359 Compare May 2, 2025 15:25
@psychedelicious psychedelicious enabled auto-merge (rebase) May 5, 2025 13:32
@hipsterusername hipsterusername disabled auto-merge May 5, 2025 13:40
@hipsterusername hipsterusername merged commit 1f63b60 into main May 5, 2025
12 checks passed
@hipsterusername hipsterusername deleted the training-model-loading-updates branch May 5, 2025 13:40
psychedelicious added a commit that referenced this pull request May 6, 2025
xiaden pushed a commit to xiaden/InvokeAI that referenced this pull request May 7, 2025
* integrate loRA

* idk anymore tbh

* enable fused matrix for quantized models

* integrate loRA

* idk anymore tbh

* enable fused matrix for quantized models

* ruff fix

---------

Co-authored-by: Sam <bhaskarmdutt@gmail.com>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backend PRs that change backend files python PRs that change python files
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants