Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
278 Open 1,694 Closed
278 Open 1,694 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(data_plane): bump TransferQueue to v0.1.8 for mooncake cpu rdma backend
#2935 opened Jun 25, 2026 by ZhiyuLi-Nvidia Contributor Loading…
4 tasks
1
[Don't merge] feat(grpo): add NRL_GEN_BENCHMARK_SKIP_TRAINING for async generation
#2930 opened Jun 25, 2026 by RayenTian Contributor • Draft
4 tasks
1
ci: Bump Megatron-Bridge to 1e8d117 CI:L1 Run doctests, unit tests, and functional tests
#2929 opened Jun 25, 2026 by svcnvidia-nemo-ci Contributor Loading…
3
refactor(eval): route AIME eval through the response dataset registry CI:L1 Run doctests, unit tests, and functional tests
#2928 opened Jun 25, 2026 by NolenLiang Contributor Loading…
2
fix(topology): exclude unknown-NVLink-domain nodes from segment selection CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2924 opened Jun 24, 2026 by terrykong Collaborator • 1/2 Loading…
2 tasks done
4
chore(docker): remove royalty-obligating codec libs from release image
#2922 opened Jun 24, 2026 by kajalj22 Contributor Loading…
2 tasks
1
fix: serialize uv installs to avoid nvidia-cutlass-dsl install race CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2921 opened Jun 24, 2026 by youngeunkwon0405 Contributor Loading…
4 tasks
@youngeunkwon0405
5
perf: batch worker port discovery CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2920 opened Jun 24, 2026 by macandro96 Contributor Loading…
4 tasks
3
test: re-enable mcore tests CI:L1 Run doctests, unit tests, and functional tests
#2919 opened Jun 24, 2026 by shanmugamr1992 Contributor Loading…
4 tasks
2
fix: improve error message when NeMo Gym returns no generation data CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2918 opened Jun 24, 2026 by yfw Contributor Loading…
4 tasks
2
fix(async-grpo): starvation diagnostics, gym logging, and dataloader exhaustion
#2917 opened Jun 24, 2026 by saumishr Contributor Loading…
4 tasks
1
feat: ThreadSafeTimer, container init timing, and Ray telemetry
#2916 opened Jun 24, 2026 by saumishr Contributor Loading…
4 tasks
1
feat: R3 gym notq router replay CI:L1 Run doctests, unit tests, and functional tests
#2915 opened Jun 24, 2026 by zyzhou5 Contributor Loading…
10
fix(data): extract env_name from list-form multi-dataset configs community-request
#2907 opened Jun 23, 2026 by yuchenwang3 Loading…
1
1
fix: fix fp8 hf_config_overrides bug CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2904 opened Jun 23, 2026 by ashors1 Contributor Loading…
4 tasks
4
fix: Reconcile #2315 and #2612 CI:L1 Run doctests, unit tests, and functional tests
#2902 opened Jun 23, 2026 by tdene Contributor Loading…
4 tasks
6
[draft] docs: add Qwen3.5 model guide and model-family hub Documentation Improvements or additions to documentation
#2900 opened Jun 23, 2026 by sharonyu-115 Contributor Loading…
4 tasks
1
2
fix: fix sglang env and re-enable sglang in CI CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI
#2898 opened Jun 23, 2026 by yuki-97 Contributor Loading…
18
feat: Update Megatron Inference API interface CI:L1 Run doctests, unit tests, and functional tests
#2891 opened Jun 22, 2026 by tdene Contributor Loading…
4 tasks
5
fix: load policy in compute dtype when optimizer holds fp32 master weights community-request waiting-on-maintainers Waiting on maintainers to respond
#2888 opened Jun 22, 2026 by Doondi-Ashlesh Loading…
1
1
feat: add multiple penalties for model behaviour CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2885 opened Jun 22, 2026 by macandro96 Contributor Loading…
4 tasks
8
feat: async colocated GRPO with Megatron inference CI:L1 Run doctests, unit tests, and functional tests
#2884 opened Jun 22, 2026 by tdene Contributor Loading…
4 tasks
4
feat: add Mistral Medium 3.5 (128B) text-only DAPO support CI:L1 Run doctests, unit tests, and functional tests
#2875 opened Jun 19, 2026 by sharonyu-115 Contributor Loading…
3 of 4 tasks
4
DRAT: fix: run Nemotron Nano v2 workplace assistant recipe
#2868 opened Jun 18, 2026 by snowmanwwg Contributor Loading…
4 tasks
1
DRAFT fix: Nano-v3 recipe run fix.
#2867 opened Jun 18, 2026 by snowmanwwg Contributor Loading…
4 tasks
1
ProTip! Mix and match filters to narrow down what you’re looking for.