Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
159 Open 1,285 Closed
159 Open 1,285 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

[WIP] Sglang Rollout Refactor community-request
#2267 opened Apr 14, 2026 by xiuhu17 • Draft
1
cp: feat: add nvidia-resiliency-ext as nvrx optional extra (2264) into r0.6.0 cherry-pick CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version) documentation Improvements or additions to documentation Run CICD
#2266 opened Apr 14, 2026 by svcnvidia-nemo-ci Loading…
3
ci: add sync-skills workflow CI Relating to CI
#2265 opened Apr 14, 2026 by ko3n1g Contributor Loading…
1
add x-token alignment foundation and arrow dataset wiring community-request needs-follow-up Issue needs follow-up
#2253 opened Apr 12, 2026 by avenkateshha Loading…
4 tasks
1
fix: preserve RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES to prevent NCCL NVSwitch bugs community-request
#2252 opened Apr 12, 2026 by dmvevents Contributor Loading…
3 tasks done
1
10
feat: Enable vllm metrics logging w/ sync
#2250 opened Apr 11, 2026 by parthmannan Contributor • Draft
4 tasks
1
feat: Add pinned memory optimizer offload for Megatron policy worker CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#2248 opened Apr 10, 2026 by snivertynv Loading…
4 tasks
@snivertynv
5
chore: update sglang to chtruong814 fork CI:L1 Run doctests, unit tests, and functional tests
#2246 opened Apr 10, 2026 by kajalj22 Contributor • Draft
2
Xtoken/off policy distillation gh community-request
#2245 opened Apr 10, 2026 by avenkateshha Loading…
4 tasks
1
feat: add PP + CP + seqpack support for automodel backend CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2242 opened Apr 9, 2026 by hemildesai Contributor • Draft
5 tasks done
9
fix: workaround for optimizer offload
#2239 opened Apr 9, 2026 by yuki-97 Contributor • Draft
1
Tk/infra
#2238 opened Apr 9, 2026 by terrykong Collaborator • Draft
4 tasks
1
feat: support convert_lora_to_hf without merge CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version) documentation Improvements or additions to documentation
#2234 opened Apr 8, 2026 by RayenTian Contributor Loading…
4 tasks
1
8
Expose hardcoded Megatron infrastructure parameters to user config community-request
#2230 opened Apr 8, 2026 by nic-nvidia Loading…
3 tasks
1
5
docs: add CUDA driver compatibility guide documentation Improvements or additions to documentation
#2227 opened Apr 7, 2026 by terrykong Collaborator Loading…
2 tasks
1
Fix save_megatron_model deadlock: pass fully_parallel_save=False during conversion community-request
#2226 opened Apr 7, 2026 by nic-nvidia Loading…
1 of 3 tasks
1
3
feat: add Gemma4 support CI:L1 Run doctests, unit tests, and functional tests
#2224 opened Apr 7, 2026 by sharonyu-115 Contributor • Draft
4 tasks
10
Full Dynamo integration
#2222 opened Apr 6, 2026 by jthomson04 • Draft
4 tasks
3
Fix preserving dataset merge for SFT community-request
#2218 opened Apr 6, 2026 by Bungmint Loading…
3
feat: add SDPO algorithm community-request needs-follow-up Issue needs follow-up
#2217 opened Apr 6, 2026 by celineltan Loading…
1 of 4 tasks
1
fix: handle PreservingDataset in dataset concatenation community-request needs-follow-up Issue needs follow-up
#2213 opened Apr 4, 2026 by RudimentaryChef Loading…
1 of 2 tasks
1
2
fix: convert_dcp_to_hf.py correctly loads saved tokenizer from DCP if detected CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2210 opened Apr 3, 2026 by trias702 Loading…
1 of 3 tasks
12
Preserve batched env evaluation in async validation rollouts community-request
#2209 opened Apr 3, 2026 by taivu1998 • Draft
1
Add timeout and memory limits to CodeEnvironment execution community-request documentation Improvements or additions to documentation
#2208 opened Apr 3, 2026 by taivu1998 • Draft
1
1
Handle invalid environment rewards explicitly across environments, rollouts, and GRPO community-request
#2207 opened Apr 3, 2026 by taivu1998 • Draft
1
ProTip! Filter pull requests by the default branch with base:main.