-
Notifications
You must be signed in to change notification settings - Fork 373
Pull requests: NVIDIA-NeMo/RL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: add online DPO training
community-request
Documentation
Improvements or additions to documentation
feat(grpo): add SAPO actor loss
community-request
Documentation
Improvements or additions to documentation
feat(grpo): support async multiple dataloaders
community-request
Documentation
Improvements or additions to documentation
fix(infra): dev pod RBAC, macOS install scripts, helm fixes
#2450
opened May 10, 2026 by
terrykong
Collaborator
Loading…
5 tasks
fix(nrl-k8s): rewrite
--config in entrypoint to honor CLI RECIPE arg
#2449
opened May 9, 2026 by
hemildesai
Contributor
Loading…
2 of 3 tasks
refactor: refactor async utils
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
fix(megatron): delegate packed CP slicing to MCore
#2445
opened May 8, 2026 by
zyzhou5
Loading…
4 tasks
feat(vllm): add delta-compressed collective refit
#2444
opened May 8, 2026 by
HollowMan6
Member
Loading…
4 tasks done
fix: fix skip_reference_policy_logprobs_calculation and skip_prev_logprobs
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2443
opened May 8, 2026 by
jinglinglingling
Loading…
feat: data plane transfer queue integration
CI:L1
Run doctests, unit tests, and functional tests
#2439
opened May 7, 2026 by
ZhiyuLi-Nvidia
Contributor
Loading…
4 tasks done
[WIP] don't review
Documentation
Improvements or additions to documentation
#2420
opened May 6, 2026 by
shuyixiong
Contributor
•
Draft
4 tasks
feat: Auto research skill
community-request
waiting-on-maintainers
Waiting on maintainers to respond
#2419
opened May 6, 2026 by
vinhngx
Contributor
Loading…
fix: handle non-contiguous tensors in IPC weight refit
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
community-request
waiting-on-customer
Waiting on the original author to respond
#2418
opened May 5, 2026 by
jlcanta
Loading…
3 of 4 tasks
feat: Support Megatron + SGLang
community-request
waiting-on-maintainers
Waiting on maintainers to respond
#2416
opened May 5, 2026 by
pengdurice
Contributor
Loading…
2 of 4 tasks
[WIP] New refit integration branch
#2413
opened May 5, 2026 by
youngeunkwon0405
Contributor
•
Draft
4 tasks
Previous Next
ProTip!
no:milestone will show everything without a milestone.