Add --svd_lowrank_niter option to resize_lora.py#2296
Merged
Conversation
Allow users to control the number of iterations for torch.svd_lowrank on large matrices. Default is 2 (matching PR #2240 behavior). Set to 0 to disable svd_lowrank and use full SVD instead. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
--svd_lowrank_niteroption toresize_lora.pyto control the number of iterations fortorch.svd_lowrankon large matrices (>2048 dims)2(same behavior as Usetorch.svd_lowrankfor large matrices inresize_lora.py#2240), set to0to disable and use full SVDniter=7for higher quality at minimal extra cost)Test plan
niter=2) runs in ~2s,niter=7in ~3s,niter=0(full SVD) in ~18min--verboseoutput is nearly identical across allnitervalues🤖 Generated with Claude Code