Skip to content

Pull requests: huggingface/peft

New pull request New
45 Open 1,988 Closed
45 Open 1,988 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Validate Super-Tuning index persistence across adapters
#3665 opened Sep 4, 2026 by DaoyuanLi2816 Contributor Loading…
1
docs: add Simplified Chinese translation (README.zh.md)
#3664 opened Sep 4, 2026 by JasonYeYuhe Loading…
1
DOC Fix broken docstring examples in peft_model and tuner models
#3657 opened Sep 3, 2026 by blipbyte Contributor Loading…
1
Fix Trainable Tokens random-init unmerge
#3656 opened Sep 3, 2026 by DaoyuanLi2816 Contributor Loading…
1
5
Raise a clear error for an invalid peft_type in from_peft_type
#3655 opened Sep 3, 2026 by Devam0311 Loading…
1
@BenjaminBossan
TST Add PEFT testing guide
#3648 opened Sep 2, 2026 by BenjaminBossan Member Loading…
1
FIX Adapter deletion and multi-adapter saving for prompt learning and adaption prompt
#3639 opened Sep 1, 2026 by amogh-nagri-11 Loading…
@BenjaminBossan
4
NoRA
#3637 opened Sep 1, 2026 by Joluck Contributor Loading…
5
FIX X-LoRA adapter lifecycle: disable_adapter, training mode and frozen classifier
#3636 opened Sep 1, 2026 by amogh-nagri-11 Loading…
1
13
fix(shadow): clear per-forward state and use partial for hooks to fix lifecycle leak
#3633 opened Aug 31, 2026 by Sravanjangam Contributor Loading…
1
7
fix(shadow): sync lm_head trainability on set_adapter for CAUSAL_LM
#3632 opened Aug 31, 2026 by Sravanjangam Contributor Loading…
1
@BenjaminBossan
5
TST Accelerate mixed adapter batches tests
#3630 opened Aug 31, 2026 by BenjaminBossan Member Loading…
2
FIX ShadowPEFT last-token pooling with left padding
#3629 opened Aug 31, 2026 by aswanth-07 Contributor Loading…
1
@BenjaminBossan
7
Filter adapter-name slots by tuner-prefix position
#3623 opened Aug 30, 2026 by Sravanjangam Contributor Loading…
@BenjaminBossan
FIX get_layer_device_map StopIteration on CPU-only device maps
#3621 opened Aug 30, 2026 by Cunninger Loading…
1
LoRA TP DTensor migration
#3614 opened Aug 28, 2026 by michaelbenayoun Member Loading…
5
Keep failed LoRA safe merges from changing base weights
#3611 opened Aug 28, 2026 by Robertboy18 Loading…
3
FEAT Add MoE-to-Dense adapter
#3604 opened Aug 25, 2026 by BenjaminBossan Member • Draft
13
Warn when rank_pattern / alpha_pattern keys match no targeted module
#3588 opened Aug 23, 2026 by Sravanjangam Contributor Loading…
1
TST Update adaption prompt tests
#3573 opened Aug 20, 2026 by BenjaminBossan Member Loading…
1
TST Improve test coverage prompt learning
#3570 opened Aug 20, 2026 by BenjaminBossan Member Loading…
1
ENH Add option to use Khatri-Rao to LoHa
#3560 opened Aug 18, 2026 by BenjaminBossan Member Loading…
1
fix: handle removal of distributed_operation in Transformers TP rework
#3553 opened Aug 14, 2026 by peft-jambot Contributor • Draft
Update UniLoRA MetaMathQA benchmark configs with tuned hyperparameters
#3552 opened Aug 14, 2026 by peft-jambot Contributor • Draft
Fix PeftMixedModel.disable_adapter to restore prior adapter state
#3543 opened Aug 13, 2026 by xquantize Loading…
1
1
ProTip! no:milestone will show everything without a milestone.