-
Notifications
You must be signed in to change notification settings - Fork 2.5k
Pull requests: huggingface/peft
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
TST Ignore floating point noise in gradient checkpointing test
#3599
opened Aug 25, 2026 by
jiqing-feng
Contributor
Loading…
FIX AdaMSS, PSOFT: fork the RNG of the actual device
#3598
opened Aug 25, 2026 by
jiqing-feng
Contributor
Loading…
Warn when the adapter-name filter removes colliding tensors during save
#3591
opened Aug 23, 2026 by
Sravanjangam
Loading…
Refuse to hot-swap adapters while they are merged into the base weights
#3590
opened Aug 23, 2026 by
Sravanjangam
Loading…
Make LoHa/LoKr merge and unmerge deterministic while in train mode
#3589
opened Aug 23, 2026 by
Sravanjangam
Loading…
Warn when rank_pattern / alpha_pattern keys match no targeted module
#3588
opened Aug 23, 2026 by
Sravanjangam
Loading…
Fix nested LoRA sub-configs silently staying dicts after save/load round-trip
#3587
opened Aug 23, 2026 by
Sravanjangam
Loading…
Fix LoRA on FSDP2-sharded models: shape inference and module hooks
#3578
opened Aug 22, 2026 by
qgallouedec
Member
Loading…
fix: support torchao v0.18.0 which removed AffineQuantizedTensor
#3571
opened Aug 20, 2026 by
peft-jambot
Contributor
Loading…
TST Improve test coverage prompt learning
#3570
opened Aug 20, 2026 by
BenjaminBossan
Member
•
Draft
ENH Add option to use Khatri-Rao to LoHa
#3560
opened Aug 18, 2026 by
BenjaminBossan
Member
Loading…
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
AI Add skill for making changes to PEFT methods
#3544
opened Aug 13, 2026 by
BenjaminBossan
Member
Loading…
Fix PeftMixedModel.disable_adapter to restore prior adapter state
#3543
opened Aug 13, 2026 by
xquantize
Loading…
Implementation for Multi Token Prediction (2507.11851)
#3541
opened Aug 12, 2026 by
githubnemo
Collaborator
•
Draft
ENH Improve BOFT forward pass, remove CUDA kernel
#3540
opened Aug 12, 2026 by
BenjaminBossan
Member
Loading…
Add fine-tuning techniques comparison notebook for conversational AI …Add comparison notebook for fine-tuning techniques for conversational AI
#3539
opened Aug 12, 2026 by
Rithika-alt
Loading…
FIX BOFT and HRA crash on grouped Conv2d layers
#3527
opened Aug 7, 2026 by
AshNicolus
Contributor
Loading…
feat: delta-based forward pass for OSF to reduce memory and compute
#3524
opened Aug 6, 2026 by
peft-jambot
Contributor
Loading…
FIX IA3 merge/unmerge for grouped feedforward convolutions
#3519
opened Aug 6, 2026 by
AshNicolus
Contributor
Loading…
Delete every auxiliary adapter and resolve the remaining active ones across layers
#3515
opened Aug 5, 2026 by
DaoyuanLi2816
Contributor
Loading…
Keep dtype and device when loading an adapter with low_cpu_mem_usage
#3509
opened Aug 4, 2026 by
vineethsaivs
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.