Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
137 Open 1,209 Closed
137 Open 1,209 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

feat: add Qwen3.5 model support
#2151 opened Mar 25, 2026 by zpqiu • Draft
4 tasks
1
1
chore: bump mbridge CI:L1 Run doctests, unit tests, and functional tests
#2150 opened Mar 25, 2026 by yuki-97 • Draft
11
fix: Set VIRTUAL_ENV and UV_PROJECT_ENVIRONMENT to venv dir CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2149 opened Mar 25, 2026 by terrykong Loading…
2 tasks
6
ci: Build RL main on Azure CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version) CI Relating to CI
#2145 opened Mar 24, 2026 by chtruong814 Loading…
4 tasks
6
feat: Add linear CE loss fusion for DPO community-request documentation Improvements or additions to documentation
#2139 opened Mar 22, 2026 by pengdurice Loading…
4 tasks done
4
ci: upgrade GitHub Actions for Node.js 24 compatibility CI Relating to CI
#2138 opened Mar 22, 2026 by ko3n1g Loading…
1 task
2
fix: allow wandb config value changes on resume community-request needs-follow-up Issue needs follow-up
#2137 opened Mar 22, 2026 by gkaplun-nvidia Loading…
2 tasks
2
fix: remove mlm workspace CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#2136 opened Mar 21, 2026 by kajalj22 • Draft
4 tasks
6
feat: Docker Blackwell / Grace Blackwell container support community-request
#2134 opened Mar 21, 2026 by sahgerlad Loading…
1 of 4 tasks
13
[WIP] Enable Dynamic Context Parallelism for long context training
#2133 opened Mar 20, 2026 by parthmannan • Draft
4 tasks
3
Xtoken/off policy distillation CI Relating to CI community-request documentation Improvements or additions to documentation
#2123 opened Mar 18, 2026 by avenkateshha • Draft
1
fix: Update build-custom-vllm.sh
#2122 opened Mar 17, 2026 by fayejf Loading…
4 tasks
2
draft: Dynamo KV Router Support
#2114 opened Mar 15, 2026 by jthomson04 • Draft
4 tasks
3
feat: Use Megatron-Bridge recipes for megatron_cfg. CI:L2 Run doctests, unit tests, functional tests, and convergence tests Performance Related to improving performance
#2096 opened Mar 11, 2026 by sfawzy-nv Loading…
4 tasks
14
feat: Support aux loss normalization in RL SFT
#2095 opened Mar 10, 2026 by pthombre • Draft
4 tasks
2
feat: custom logits processor
#2093 opened Mar 10, 2026 by cmunley1 Loading…
4 tasks
2
feat: nemo gym vlm support CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2092 opened Mar 9, 2026 by cmunley1 Loading…
4 tasks
11
Fix grammar and typos in README
#2091 opened Mar 9, 2026 by terrykong Loading…
1 task
2
feat: Add Eagle3 online speculative decoding support documentation Improvements or additions to documentation
#2078 opened Mar 6, 2026 by isomap Loading…
4 tasks
1
31
fix: add Qwen3.5 related changes
#2076 opened Mar 6, 2026 by zpqiu Loading…
3 of 9 tasks
6
feat: support qwen-omni grpo training recipe community-request documentation Improvements or additions to documentation
#2073 opened Mar 6, 2026 by yuekaizhang Loading…
4 tasks
11
feat: [NemoRL][Efficiency] Efficiency instrumentation for different RL steps
#2071 opened Mar 5, 2026 by saumishr • Draft
3 of 4 tasks
2
feat(sft): add DataPrefetcher for background data preprocessing community-request
#2064 opened Mar 4, 2026 by dafu-wu Loading…
4 tasks done
6
Adding On-Policy Self-Distillation to Nemo-RL community-request
#2063 opened Mar 4, 2026 by Hoponga Loading…
4 tasks
33
ci: Temp disable megatron lora grpo tests CI:docs Run doctest
#2062 opened Mar 4, 2026 by chtruong814 Loading…
4 tasks
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.