Skip to content

Pull requests: huggingface/transformers

New pull request New
1,284 Open 24,704 Closed
1,284 Open 24,704 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

Fix GraniteMoeHybrid _update_mamba_mask crash on attention-only models
#45514 opened Apr 19, 2026 by tianhaocui Loading…
1
1
[Qwen3.5] Fix Qwen3.5 linear attention multi-token cached forward
#45513 opened Apr 19, 2026 by kashif Contributor Loading…
6 tasks
2
[OutputRecorder] re.search on layer_name
#45512 opened Apr 19, 2026 by eustlb Contributor Loading…
3
Fix NaN in Gemma3/EmbeddingGemma when batching mixed-length sequences…
#45511 opened Apr 19, 2026 by Kabir08 Loading…
3 of 6 tasks
1
cache_utils: fix QuantizedLayer to correctly propagate reorder_cache, crop, and batch ops to quantized buffers
#45510 opened Apr 19, 2026 by GitGlimpse895 Loading…
1 of 6 tasks
Fix get_device_properties crash when CUDA is installed but no GPU
#45509 opened Apr 18, 2026 by Jah-yee Loading…
1
1
[Doc] Fix 'tokenized' -> 'tokenizer' typo in streamer docstrings
#45508 opened Apr 18, 2026 by avasis-ai Loading…
Add full GGUF loading support for GPT‑OSS (fixes #43366, supersedes #43757) latest
#45506 opened Apr 18, 2026 by sirzechs66 Loading…
5 of 6 tasks
1
4
Add full GGUF loading support for GPT‑OSS (fixes #43366, supersedes #43757) latest
#45500 opened Apr 18, 2026 by sirzechs66 • Draft
5 of 6 tasks
1
2
Add V-JEPA 2.1 inference support
#45497 opened Apr 17, 2026 by davevanveen Loading…
5 of 6 tasks
1
1
Fix: propagate quantization_config to text sub-config for composite models in AutoModelForCausalLM
#45494 opened Apr 17, 2026 by lvliang-intel Loading…
1
[WIP] Major processing refactor
#45493 opened Apr 17, 2026 by zucchini-nlp Member Loading…
3
Fix: modular image processors
#45492 opened Apr 17, 2026 by zucchini-nlp Member Loading…
5
Add ctsm model
#45490 opened Apr 17, 2026 by kashif Contributor Loading…
6 tasks
2
Align gemma3n cache sharing to gemma4
#45489 opened Apr 17, 2026 by Cyrilvallez Member Loading…
8
Fix model parallel issue for altclip model and ChineseClip model
#45487 opened Apr 17, 2026 by kaixuanliu Contributor Loading…
1
fix: return empty tuple from import_protobuf_decode_error when protobuf is unavailable
#45486 opened Apr 16, 2026 by jw9603 Contributor Loading…
4 of 5 tasks
1
[serve] Update tool call to switch to parse_response
#45485 opened Apr 16, 2026 by SunMarc Member Loading…
21
[Conversion Mapping] Small fixups
#45483 opened Apr 16, 2026 by vasqu Contributor Loading…
7
Update quants tests
#45480 opened Apr 16, 2026 by SunMarc Member Loading…
5
Blockwise mask fn as opt arg in all masking functions
#45477 opened Apr 16, 2026 by zucchini-nlp Member Loading…
6
[Don't merge] Call CI workflow
#45476 opened Apr 16, 2026 by ydshieh Collaborator Loading…
3
chore(qa): split out mlinter
#45475 opened Apr 16, 2026 by tarekziade Collaborator Loading…
@tarekziade
3
Fix EP: RouterParallel shape, tp_plan property, grouped_mm sentinels
#45473 opened Apr 16, 2026 by AmineDiro Member Loading…
2 tasks done
1
Add EXAONE 4.5 implementations
#45471 opened Apr 16, 2026 by nuxlear Contributor Loading…
3 of 6 tasks
26
ProTip! no:milestone will show everything without a milestone.