Skip to content

Pull requests: huggingface/peft

New pull request New
35 Open 1,674 Closed
35 Open 1,674 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

DOC Fix incorrect imports in helpers.py docstring examples
#3249 opened May 20, 2026 by blipbyte Loading…
[BUG FIX] tuners/lora/eva: fix label mask guard using 'in' instead of hasattr for dict
#3247 opened May 20, 2026 by Dev-X25874 Loading…
2
chore: add missing return type annotations in import_utils and other
#3245 opened May 19, 2026 by lphuc2250gma Loading…
TST Remove unnecessary use of trust_remote_code
#3242 opened May 19, 2026 by BenjaminBossan Member Loading…
1
1
Fix prepare model for compiled hotswap requires grad
#3241 opened May 19, 2026 by BenjaminBossan Member Loading…
1
fix(tuners): use self.active_adapters (list) when guarding requires_grad for newly created sub-adapter modules
#3239 opened May 17, 2026 by Chessing234 Contributor Loading…
fix(tuners/lora/torchao): make get_apply_tensor_subclass optional (#3223)
#3234 opened May 13, 2026 by Anai-Guo Contributor Loading…
3 tasks
1
4
Guard _convert_peft_config_moe against regex-string target_modules
#3232 opened May 12, 2026 by 1fanwang Loading…
1
4
FIX Transformers weight conversion PEFT model prefix
#3230 opened May 12, 2026 by BenjaminBossan Member Loading…
7
FIX BEFT merge on bias-less layers; RandLoRA save_projection default
#3227 opened May 12, 2026 by kashif Contributor Loading…
3
feat: registry-based dispatch for resolve_lora_variant in Linear layer
#3219 opened May 9, 2026 by isha822 • Draft
15
fix(tuners): guard child.weight access in _replace_module for non-linear modules
#3213 opened May 4, 2026 by Chessing234 Contributor Loading…
1
fix(gralora): use _cast_input_dtype in forward instead of raw .to()
#3209 opened May 2, 2026 by Chessing234 Contributor Loading…
fix(pvera): use _cast_input_dtype in forward instead of raw .to()
#3208 opened May 2, 2026 by Chessing234 Contributor Loading…
1
feat(lora): Add FIM-guided adaptive LoRA rank allocation (FimConfig + initialize_lora_fim_ranks)
#3204 opened Apr 28, 2026 by ramkrishs • Draft
3
ENH Optimize HRA forward for better memory efficiency
#3185 opened Apr 22, 2026 by BenjaminBossan Member Loading…
3
fix(tuners/lora/bnb): normalize output device for CPU-offloaded BnB layers
#3181 opened Apr 21, 2026 by Anai-Guo Contributor Loading…
1
13
Use _cast_input_dtype in poly Linear.forward
#3177 opened Apr 20, 2026 by Chessing234 Contributor Loading…
2
Use _cast_input_dtype in vera Linear.forward
#3172 opened Apr 17, 2026 by Chessing234 Contributor Loading…
1
Use _cast_input_dtype in FourierFTLinear.forward
#3170 opened Apr 17, 2026 by Chessing234 Contributor Loading…
2
Fix DeloraLinear.unmerge subtracting un-cast delta weight
#3166 opened Apr 16, 2026 by Chessing234 Contributor Loading…
2
Fix C3ALinear.forward chaining active adapters through x instead of summing
#3164 opened Apr 15, 2026 by Chessing234 Contributor Loading…
3
FIX IA3 _ConvNd.unmerge bias uses torch.mul instead of torch.div
#3149 opened Apr 11, 2026 by Chessing234 Contributor Loading…
4
Generic quantization support for BOFT, MiSS, VeRA wip
#3117 opened Mar 25, 2026 by BenjaminBossan Member Loading…
11
FIX Several bugs when adding merged LoRA weights
#3111 opened Mar 18, 2026 by BenjaminBossan Member Loading…
16
ProTip! Updated in the last three days: updated:>2026-05-17.