-
Notifications
You must be signed in to change notification settings - Fork 512
Pull requests: NVIDIA-NeMo/RL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(sglang): megatron backend weight refit for sglang rollouts
#3612
opened Aug 12, 2026 by
Kh4L
Loading…
fix: remove the mcore async_engine flag
CI:L1
Run doctests, unit tests, and functional tests
#3611
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
ci: Distinguish between normal nightlies and mcore smoke tests
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#3610
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
fix: ensure base configs don't use nvshmem refit
CI:L1
Run doctests, unit tests, and functional tests
#3609
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
feat: mopd teacher topk
Documentation
Improvements or additions to documentation
#3608
opened Aug 12, 2026 by
macandro96
Contributor
Loading…
4 tasks
fix: skip the HF refit-info handshake for MInf
CI:L1
Run doctests, unit tests, and functional tests
#3607
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
ci: AUT-1111 add Megatron test workflow dispatch
CI:L2
Run doctests, unit tests, functional tests, and convergence tests
CI
Relating to CI
#3606
opened Aug 12, 2026 by
svcnemo-autobot
Contributor
Loading…
fix: model save directly after validation
CI:L1
Run doctests, unit tests, and functional tests
#3605
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
fix: Add torch-memory-saver to the mcore extra deps
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#3602
opened Aug 12, 2026 by
tdene
Contributor
Loading…
4 tasks
Update MLPerf Training GRPO dataset
community-request
#3601
opened Aug 12, 2026 by
filaretov
Loading…
fix: stop the launcher environment leaking into checkpoint config.yaml
community-request
#3600
opened Aug 12, 2026 by
mario-at-intercom
Loading…
3 of 4 tasks
fix(async-grpo): eliminate prompt skips across checkpoint save/restore
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
ci: Bump Megatron-Bridge to 600d069
CI:L1
Run doctests, unit tests, and functional tests
#3597
opened Aug 12, 2026 by
svcnvidia-nemo-ci
Contributor
Loading…
feat: add DeepSeek V4 Flash support - Automodel path
Documentation
Improvements or additions to documentation
feat(sc): restart dead generation shards and re-admit them at the next refit
#3592
opened Aug 12, 2026 by
terrykong
Collaborator
•
4/4
Loading…
3 of 4 tasks
feat(sc): keep training when a generation shard dies
#3591
opened Aug 12, 2026 by
terrykong
Collaborator
•
3/4
Loading…
3 of 4 tasks
feat(sc): track generation fleet health and route NeMo-Gym through NeMo-RL
#3590
opened Aug 12, 2026 by
terrykong
Collaborator
•
2/4
Loading…
3 of 4 tasks
feat(sc): contain rollout failures in the SingleController path
#3589
opened Aug 12, 2026 by
terrykong
Collaborator
•
1/4
Loading…
3 of 4 tasks
fix: Update comments to include implementation details link
CI:docs
Run doctest
#3588
opened Aug 12, 2026 by
youngeunkwon0405
Contributor
Loading…
4 tasks
Nano3.5 v2 launch
Documentation
Improvements or additions to documentation
#3586
opened Aug 11, 2026 by
mehraakash
Contributor
•
Draft
4 tasks
feat(rollout): add partial recovery benchmark telemetry
#3585
opened Aug 11, 2026 by
macandro96
Contributor
•
Draft
Previous Next
ProTip!
Adding no:label will show everything without a label.