Bump peft from 0.17.1 to 0.18.0

[dependabot]

Bumps peft from 0.17.1 to 0.18.0.

Release notes

Sourced from peft's releases.

0.18.0: RoAd, ALoRA, Arrow, WaveFT, DeLoRA, OSF, and more

Highlights

FIXME update list of all changes, so some more commits were added

New Methods

RoAd

@​ppetrushkov added RoAd: 2D Rotary Adaptation to PEFT in #2678. RoAd learns 2D rotation matrices that are applied using only element-wise multiplication, thus promising very fast inference with adapters in unmerged state.

Remarkably, besides LoRA, RoAd is the only PEFT method that supports mixed adapter batches. This means that when you have loaded a model with multiple RoAd adapters, you can use all of them for different samples in the same batch, which is much more efficient than switching adapters between batches:

model = PeftModel.from_pretrained(base_model, <path-to-road-adapter-A>, adapter_name="adapter-A")
model.add_adapter("adapter-B", <path-to-road-adapter-B>)
inputs = ...  # input with 3 samples
apply adapter A to sample 0, adapter B to sample 1, and use the base model for sample 2:
adapter_names = ["adapter-A", "adapter-B", "base"]
output_mixed = model(**inputs, adapter_names=adapter_names)
gen_mixed = model.generate(**inputs, adapter_names=adapter_names)

ALoRA

Activated LoRA is a technique added by @​kgreenewald in #2609 for causal language models, allowing to selectively enable LoRA adapters depending on a specific token invocation sequence in the input. This has the major benefit of being able to re-use most of the KV cache during inference when the adapter is only used to generate part of the response, after which the base model takes over again.

Arrow & GenKnowSub

@​TheTahaaa contributed not only support for Arrow, a dynamic routing algorithm between multiple loaded LoRAs in #2644, but also GenKnowSub, a technique built upon Arrow where the 'library' of LoRAs available to Arrow is first modified by subtracting general knowledge adapters (e.g., trained on subsets of Wikipedia) to enhance task-specific performance.

WaveFT

Thanks to @​Bilican, Wavelet Fine-Tuning (WaveFT) was added to PEFT in #2560. This method trains sparse updates in the wavelet domain of residual matrices, which is especially parameter efficient. It is very interesting for image generation, as it promises to generate diverse outputs while preserving subject fidelity.

DeLoRA

Decoupled Low-rank Adaptation (DeLoRA) was added by @​mwbini in #2780. This new PEFT method is similar to DoRA in so far as it decouples the angle and magnitude of the learned adapter weights. However, DeLoRA implements this in a way that promises to better prevent divergence. Moreover, it constrains the deviation of the learned weight by imposing an upper limit of the norm, which can be adjusted via the delora_lambda parameter.

OSF

Orthogonal Fine-Tuning (OSF) was added by @​NikhilNayak-debug in #2685. By freezing the high-rank subspace of the targeted weight matrices and projecting gradient updates to a low-rank subspace, OSF achieves good performance on continual learning tasks. While it is a bit memory intensive for standard fine-tuning processes, it is definitely worth checking out on tasks where performance degradation of previously learned tasks is a concern.

Enhancements

Text generation benchmark

... (truncated)

Commits

• 77daa8d Release: v0.18.0 (#2908)
• 52e8659 Add forward compat. for tied_weights_keys dicts (#2902)
• 7d4c9fd CI: Fix issues caused by pytest v9 (#2904)
• e82e72a FIX Prefix tuning with Qwen3 issue (#2883)
• ff00848 FIX: Exploit trust_remote_code in prompt tuning (#2896)
• 0eb4668 TST Fix 4bit regression test on XPU (#2843)
• ed00f24 DOC Update arxiv links to hf
• 30a19a0 Fix #2826: implement gradient checkpoint callbacks (#2860)
• d43b315 Post rc-release version bump (#2875)
• 5d58b51 Release 0.18.0.rc0 (#2849)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)