-
Notifications
You must be signed in to change notification settings - Fork 34.4k
Pull requests: huggingface/transformers
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Reject uneven splits in Chunk weight conversions
#48405
opened Aug 29, 2026 by
Ki-Seki
Contributor
Loading…
4 of 6 tasks
Fix AyaVision default vision config not being instantiable
#48402
opened Aug 28, 2026 by
meryemsakin
Loading…
3 tasks done
Fix dataclass and nested sequence serialization in GenerationConfig.to_json_string
#48399
opened Aug 28, 2026 by
YeshwanthRajSelvaraj
Loading…
3 tasks done
Enforce TRF057 everywhere: drop its allowlist and cutoff date
#48398
opened Aug 28, 2026 by
tarekziade
Collaborator
Loading…
Bump the actions group across 1 directory with 13 updates
dependencies
Pull requests that update a dependency file
github_actions
Pull requests that update GitHub Actions code
#48395
opened Aug 28, 2026 by
dependabot
Bot
Loading…
Fix flaky
MellumModelTest.test_load_balancing_loss
#48389
opened Aug 28, 2026 by
subin9
Contributor
Loading…
[Model] Add PP-DocLayoutV4 Model Support
#48387
opened Aug 28, 2026 by
maxiaolong03
Loading…
3 of 5 tasks
Add MOSS-Transcribe-Diarize model
New model
#48386
opened Aug 28, 2026 by
itazap
Collaborator
Loading…
[serge] Fix 6 integration tests for model
mluke failing with other (other (6))
#48385
opened Aug 28, 2026 by
sergereview
Bot
Loading…
Give each tensor parallel model in a process its own device mesh
#48383
opened Aug 28, 2026 by
qgallouedec
Member
Loading…
Let a thread that shares the model take a turn on it under continuous…
#48382
opened Aug 27, 2026 by
qgallouedec
Member
•
Draft
Modernize ConvNextV2, ResNet, RegNet, RTDetrResnet, SwinV2, Swin2SR
#48378
opened Aug 27, 2026 by
sbucaille
Contributor
Loading…
2 of 5 tasks
handle transpose during model loading with TP (Qwen3-VL-MoE)
#48373
opened Aug 27, 2026 by
3outeille
Member
Loading…
Carry weight_global_scale when decompressing NVFP4 MoE experts
#48372
opened Aug 27, 2026 by
Bluear7878
Contributor
Loading…
fix qwen4exp-fp8 ple embedding
#48368
opened Aug 27, 2026 by
JJJYmmm
Contributor
Loading…
1 of 4 tasks
This PR generalizes continuous batching graph support from CUDA-only …
#48365
opened Aug 27, 2026 by
sywangyi
Contributor
Loading…
fix(generation): Enforce the auto-compile cache check for encoder-decoder models
#48364
opened Aug 27, 2026 by
harshaljanjani
Contributor
Loading…
4 tasks done
[Tag issues / labels that should be included in the next patch
DSA] Fix vanillas SDPA with padding
for patch
#48363
opened Aug 27, 2026 by
vasqu
Collaborator
Loading…
Unpin the bert copy markers, and delete the ones CI never enforced
#48362
opened Aug 27, 2026 by
ArthurZucker
Collaborator
Loading…
Add --experts-implementation flag to transformers serve
#48361
opened Aug 27, 2026 by
NathanHB
Member
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.