-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Pull requests: huggingface/peft
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(save_and_load): save base_layer.bias for bias="lora_only"
#3307
opened Jun 7, 2026 by
Anai-Guo
Contributor
Loading…
TST Add tests for hotswapping targeted LoRA parameters
#3304
opened Jun 5, 2026 by
BenjaminBossan
Member
Loading…
Separate, embeddable method comparison space
#3303
opened Jun 5, 2026 by
githubnemo
Collaborator
Loading…
FIX Bug when targeting an nn.Parameter on the root module
#3302
opened Jun 5, 2026 by
BenjaminBossan
Member
Loading…
ENH Add KaSA (Knowledge-aware Singular-value Adaptation) as a LoRA variant
#3298
opened Jun 2, 2026 by
robbiebusinessacc
•
Draft
Created tutorial detailing how to do differentially private PEFT fine-tuning of huggingface transformer models using FastDP
#3297
opened Jun 2, 2026 by
lmarchyok
Loading…
Bump the third-party-actions group with 3 updates
dependencies
Pull requests that update a dependency file
github_actions
Pull requests that update GitHub Actions code
#3295
opened Jun 1, 2026 by
dependabot
Bot
Loading…
fix(utils): call empty_cache() after fp16→fp32 casts in prepare_model_for_kbit_training
#3293
opened May 31, 2026 by
umutonuryasar
Loading…
DOC Fix incorrect LoRA references in hira and ln_tuning model docstrings
#3291
opened May 30, 2026 by
javierdejesusda
Contributor
Loading…
FIX: inject_adapter incorrectly propagates inference_mode to active adapters
#3290
opened May 30, 2026 by
kiritozc
Loading…
Add default target_modules for nemotron_h hybrid Mamba-MoE models
#3289
opened May 29, 2026 by
A1c0r-Z
Loading…
FIX Remove duplicate VBLoRAConfig entry from peft.__all__
#3279
opened May 28, 2026 by
SHAI-Akshay-Tripathi
Loading…
DOC: fix adapter_names parameter name in set_requires_grad docstrings
#3271
opened May 27, 2026 by
kratos0718
Loading…
docs(prepare_model_for_kbit_training): note the ~0.5–1 GB CUDA reserved overhead (#3265)
#3267
opened May 26, 2026 by
Anai-Guo
Contributor
Loading…
2 tasks
Fail loud on save_pretrained() for unsharded LoRA tensors
#3251
opened May 21, 2026 by
akshansh47
Loading…
Guard _convert_peft_config_moe against regex-string target_modules
#3232
opened May 12, 2026 by
1fanwang
Loading…
FIX BEFT merge on bias-less layers; RandLoRA save_projection default
#3227
opened May 12, 2026 by
kashif
Contributor
Loading…
feat: registry-based dispatch for resolve_lora_variant in Linear layer
#3219
opened May 9, 2026 by
isha822
Loading…
ENH Optimize HRA forward for better memory efficiency
#3185
opened Apr 22, 2026 by
BenjaminBossan
Member
Loading…
fix(tuners/lora/bnb): normalize output device for CPU-offloaded BnB layers
#3181
opened Apr 21, 2026 by
Anai-Guo
Contributor
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.