-
Notifications
You must be signed in to change notification settings - Fork 89
Pull requests: NVIDIA-NeMo/Automodel
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: make MistralCommonBackend inherit from PreTrainedTokenizerBase
r0.3.0
Add for cherry-pick into release branch r0.3.0
#1505
opened Mar 9, 2026 by
akoumpa
Loading…
3 tasks
fix: forward-compatible _patched_get_init_context for transformers v5.3.0
#1504
opened Mar 9, 2026 by
HuiyingLi
Loading…
2 tasks done
feat: add pipeline parallelism support for knowledge distillation
#1500
opened Mar 9, 2026 by
Separius
Loading…
fix: skip model.to(device) after checkpoint loading (tied params + FSDP)
#1489
opened Mar 8, 2026 by
terrykong
Loading…
1 of 2 tasks
cp: feat: add neat packing (greedy knapsack) for LLM and VLM datasets
#1485
opened Mar 7, 2026 by
HuiyingLi
Loading…
fix: attach CP attention-mask hooks for dense (non-TE) context parallelism
#1470
opened Mar 6, 2026 by
hemildesai
Loading…
1 of 2 tasks
fix: Log exception and error in FirstRankPerNode before exiting
#1468
opened Mar 6, 2026 by
athitten
Loading…
3 tasks
feat: MFU logging in train recipes
community-request
#1413
opened Feb 28, 2026 by
SwekeR-463
Loading…
1 of 3 tasks
feat: Add native Comet ML experiment tracking
community-request
#1411
opened Feb 27, 2026 by
LoganVegnaSHOP
Loading…
6 tasks
docs: add retriever docs
docs-only
With great power comes great responsibility.
#1407
opened Feb 27, 2026 by
akoumpa
Loading…
3 tasks
fix: cherry-pick combined projection fixes (#1324, #1357) into r0.2.1
#1388
opened Feb 25, 2026 by
HuiyingLi
Loading…
2 tasks
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.