Skip to content

Pull requests: NVIDIA/NeMo-RL

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

feat: Add Megatron-LM based training CI Relating to CI
#439 opened May 23, 2025 by SahilJain314 Loading…
Add llm-as-a-judge environment
#438 opened May 23, 2025 by HeyyyyyyG Loading…
4 tasks
Use llm export for refit
#435 opened May 21, 2025 by yfw Draft
4 tasks
fix: Changes to support ray job submit
#432 opened May 21, 2025 by hemildesai Draft
4 tasks
feat: default to UV_CACHE_DIR from within the container documentation Improvements or additions to documentation
#427 opened May 21, 2025 by terrykong Loading…
4 tasks
feat: use async vllm engine (only used in unit tests) CI:L0 Run doctests and unit tests
#418 opened May 20, 2025 by parthchadha Loading…
4 tasks
feat: Add IFEval Environment
#412 opened May 19, 2025 by abukharin-nv Loading…
cp: Minor Change CI Relating to CI
#399 opened May 15, 2025 by chtruong814 Draft
4 tasks
DRAFT - Yash/llama nemotron data
#385 opened May 15, 2025 by yashaswikarnati Draft
4 tasks
[DO NOT MERGE] dummy PR to run DPO functional test CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI
#374 opened May 13, 2025 by ashors1 Draft
4 tasks
feat: general fsdp2 on non-MoE models + HF TP plan CI:docs Run doctest CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#352 opened May 12, 2025 by yuki-666 Loading…
4 tasks
feat: async ray monitoring now tracks system memory CI:L1 Run doctests, unit tests, and functional tests
#349 opened May 10, 2025 by terrykong Loading…
feat: add script to redact hparam paths from tensorboard logs CI:L0 Run doctests and unit tests
#347 opened May 9, 2025 by terrykong Loading…
feat: add data shuffle option
#334 opened May 7, 2025 by ZhiyuLi-Nvidia Loading…
2 of 4 tasks
feat: code execution & tool use r0.3.0 Release r0.3.0
#322 opened May 6, 2025 by KiddoZhu Loading…
attention mask fixes
#301 opened Apr 30, 2025 by ahmadki Loading…
4 tasks
DRAFT: Added sequence packing
#300 opened Apr 30, 2025 by ahmadki Loading…
4 tasks
feat: remove manual refit param CI:L1 Run doctests, unit tests, and functional tests
#292 opened Apr 29, 2025 by yuki-666 Draft
4 tasks
ci: Small fixes for automation to publish pypi package and bump version 0.3.0rc0 CI Relating to CI
#277 opened Apr 28, 2025 by ko3n1g Loading…
4 tasks
refactor: clean up code CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#262 opened Apr 24, 2025 by ashors1 Loading…
4 tasks
Added head-node-only hf download
#254 opened Apr 23, 2025 by SahilJain314 Loading…
docs: improve cluster documentation documentation Improvements or additions to documentation
#232 opened Apr 19, 2025 by KiddoZhu Loading…
ProTip! Filter pull requests by the default branch with base:main.