-
Notifications
You must be signed in to change notification settings - Fork 381
Pull requests: NVIDIA-NeMo/RL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(xtoken): cross-tokenizer off-policy distillation
community-request
Documentation
Improvements or additions to documentation
#2508
opened May 16, 2026 by
avenkateshha
Loading…
3 tasks
feat(muon): add Muon optimizer support to the DTensor backend
community-request
Documentation
Improvements or additions to documentation
#2505
opened May 15, 2026 by
bzantium
Loading…
4 tasks done
fix(distillation): teacher block drops user policy overrides via YAML anchor
community-request
#2504
opened May 15, 2026 by
bzantium
Loading…
1 of 4 tasks
feat: Adds a Comet logger
community-request
Documentation
Improvements or additions to documentation
#2503
opened May 15, 2026 by
louisfaury
Loading…
4 tasks done
feat: per-dataset validation dataloaders for GRPO and Distillation
community-request
#2502
opened May 15, 2026 by
bzantium
Loading…
2 of 4 tasks
fix: pass trust_remote_code=True to remaining AutoConfig.from_pretrained sites
community-request
#2496
opened May 15, 2026 by
bzantium
Loading…
1 of 4 tasks
feat: Discard weight when finish generation in the main loop
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2495
opened May 14, 2026 by
guyueh1
Contributor
Loading…
4 tasks
fix: remove stale Penguin reference from async_utils comment
community-request
waiting-on-maintainers
Waiting on maintainers to respond
#2493
opened May 14, 2026 by
lonexreb
Loading…
feat: Add support for GLM 5.1 GRPO
Documentation
Improvements or additions to documentation
#2489
opened May 13, 2026 by
slikhite-1
Contributor
Loading…
4 tasks
chore: upgrade sglang from v0.5.10 to v0.5.11
CI:L1
Run doctests, unit tests, and functional tests
#2481
opened May 13, 2026 by
kajalj22
Contributor
Loading…
2 tasks
[draft] feat: add flextron support to Hybrid models
#2474
opened May 12, 2026 by
rohitrango
Contributor
•
Draft
2 of 4 tasks
feat: add AIME-2026 benchmark.
CI:L1
Run doctests, unit tests, and functional tests
community-request
Documentation
Improvements or additions to documentation
#2469
opened May 12, 2026 by
xxman-google
Contributor
Loading…
4 tasks done
feat: add HMMT eval benchmark.
community-request
Documentation
Improvements or additions to documentation
waiting-on-customer
Waiting on the original author to respond
#2468
opened May 12, 2026 by
xxman-google
Contributor
Loading…
2 of 4 tasks
feat: [NemoRL] Introduce WeightSynchronizer ABC with IPC/HTTP/NCCL transports
#2466
opened May 11, 2026 by
saumishr
Loading…
4 tasks
Previous Next
ProTip!
Updated in the last three days: updated:>2026-05-13.