Implement peft.fuse_params / unfuse_params for LoRA weight fusion - #764
Open
Ayush7614 wants to merge 1 commit into
Open
Implement peft.fuse_params / unfuse_params for LoRA weight fusion#764Ayush7614 wants to merge 1 commit into
Ayush7614 wants to merge 1 commit into
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
These public APIs were documented and exported but raised NotImplementedError, blocking LoRA-free inference after fine-tuning. Fold a@b into kernel/w with a reversible unfuse path, covering Dense, Einsum, and DenseGeneral layouts.
Ayush7614
force-pushed
the
feat/peft-fuse-unfuse-params
branch
2 times, most recently
from
July 28, 2026 21:35
e20042b to
d4abc31
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
peft.fuse_params/peft.unfuse_paramsAPIs so LoRA adapters can be folded into basekernel/wweights for LoRA-free inference.kernel += a @ b), Einsum, and DenseGeneral layouts (including Gemmawweight names and rank-contract + permute when needed).unfuse_paramscan reverse the merge;split_paramscan then drop them for deployment.w-named einsum fusion, no-op trees, and unsupported layouts.peft/README.mdwith a concrete usage example.Test plan
python -m pytest gemma/peft/_tree_utils_test.py -v(7 passed)