Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
121 Open 1,126 Closed
121 Open 1,126 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

refit latest update based on ahmads refactor
#1993 opened Feb 19, 2026 by shanmugamr1992 Loading…
4 tasks
22
Add is_async to CheckpointingConfig TypedDict community-request
#1991 opened Feb 19, 2026 by dmvevents Loading…
3 tasks
1
feat: Switch to mcore upstream main CI:L2 Run doctests, unit tests, functional tests, and convergence tests Run CICD
#1990 opened Feb 19, 2026 by ahmadki • Draft
4 tasks
1
feat: Nano v3 RL Recipe
#1989 opened Feb 18, 2026 by yfw • Draft
4 tasks
tests: add a diagnostic script for prefix caching naning CI:docs Run doctest documentation Improvements or additions to documentation
#1987 opened Feb 18, 2026 by terrykong Loading…
4 tasks
5
Gdpo
#1986 opened Feb 18, 2026 by nbasyl Loading…
4 tasks
22
feat: async nemo gym
#1985 opened Feb 18, 2026 by terrykong • Draft
4 tasks
1
ci: Remove environments CI Relating to CI
#1981 opened Feb 18, 2026 by ko3n1g • Draft
4 tasks
3
feat: expose ability to configure port ranges
#1976 opened Feb 17, 2026 by ananthsub • Draft
4 tasks
docs: fern migration
#1975 opened Feb 17, 2026 by lbliii Loading…
@lbliii
22
Add FLOPs tracking for nemotronh
#1971 opened Feb 17, 2026 by tejasprabhune Loading…
4 tasks done
1
build: Add vllm arm precompiled wheel env variable CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#1970 opened Feb 17, 2026 by ananthsub Loading…
1 of 4 tasks
1
3
perf: MXFP8 training with fp8_param_gather deepseek Related to deepseek 671b Performance Related to improving performance super-v3
#1969 opened Feb 17, 2026 by guyueh1 • Draft
4 tasks
@guyueh1
Refit functionality
#1967 opened Feb 16, 2026 by shanmugamr1992 Loading…
4 tasks
chore: update transformers to v5 and automodel to latest main in dtensor v2 CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI
#1962 opened Feb 15, 2026 by hemildesai Loading…
28
feat: use ray.put to reduce overhead of repeated arguments super-v3
#1944 opened Feb 14, 2026 by guyueh1 Loading…
4 tasks
3
feat: Add HybridEP support for MoE expert parallelism
#1942 opened Feb 13, 2026 by seonjinn Loading…
4 tasks
6
Shaunak/vllm specdec metrics community-request documentation Improvements or additions to documentation needs-follow-up Issue needs follow-up
#1941 opened Feb 13, 2026 by shaunjoshi Loading…
4 tasks
11
Remove do_not_average_loss; undo Megatron loss averaging in RL code
#1940 opened Feb 13, 2026 by yaoyu-33 Loading…
1
build: Update dockerfile to support Nsight install on arm platforms CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#1939 opened Feb 12, 2026 by ananthsub Loading…
4 tasks
1
feat: Support top-p and top-k
#1938 opened Feb 12, 2026 by zhandaz Loading…
2 of 4 tasks
13
Fix mcore inference
#1931 opened Feb 12, 2026 by shanmugamr1992 Loading…
4 tasks
fix: Fix device mismatch when DPO runs validation at start with CPU offload (Nemotron MoE) CI:L1 Run doctests, unit tests, and functional tests
#1930 opened Feb 12, 2026 by RayenTian • Draft
4 tasks
feat: add draft model support community-request documentation Improvements or additions to documentation needs-follow-up Issue needs follow-up
#1921 opened Feb 10, 2026 by shaunjoshi • Draft
4 tasks
6
refactor: refactor loss function
#1920 opened Feb 10, 2026 by yuki-97 • Draft
7
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.