Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
169 Open 1,304 Closed
169 Open 1,304 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: refactor xtokenizer support
#2299 opened Apr 20, 2026 by RayenTian Contributor • Draft
4 tasks
1
docs: fix grammar and typos in README
#2298 opened Apr 20, 2026 by terrykong Collaborator Loading…
1
feat: Add interleaved round-robin scheduling for Sync generation
#2297 opened Apr 20, 2026 by parthmannan Contributor • Draft
4 tasks
1
fix(nemo-gym): preserve VLM prompt parity in NeMo-Gym rollouts community-request
#2296 opened Apr 19, 2026 by taivu1998 Loading…
1
fix(grpo): add GDPO rollout guardrails and env stop-string defaults community-request
#2295 opened Apr 19, 2026 by taivu1998 Loading…
1
perf: Perf script changes for v0.6 CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2294 opened Apr 19, 2026 by guyueh1 Contributor Loading…
4 tasks
1
feat: add cpu_serialize weight transfer transport for colocated refit community-request Documentation Improvements or additions to documentation
#2293 opened Apr 19, 2026 by howard989 Loading…
3 of 4 tasks
@ZhiyuLi-Nvidia
1
ci: Run nemo gym unit tests on Github CI:L0 Run doctests and unit tests CI Relating to CI
#2292 opened Apr 19, 2026 by chtruong814 Contributor Loading…
4 tasks
7
perf: selective activation checkpointing feature support
#2280 opened Apr 17, 2026 by seonjinn Contributor Loading…
4 tasks
@seonjinn
8
perf: support fine-grained activation offloading
#2279 opened Apr 17, 2026 by seonjinn Contributor Loading…
4 tasks
@seonjinn
7
perf: enable MoE GroupedGEMM for MoE models
#2278 opened Apr 17, 2026 by seonjinn Contributor Loading…
4 tasks
@seonjinn
6
fix: forward HF env vars to policy worker runtime_env
#2272 opened Apr 15, 2026 by kajalj22 Contributor • Draft
2 tasks
1
fix: include scalar float/int in metric aggregation community-request needs-follow-up Issue needs follow-up
#2271 opened Apr 15, 2026 by sebawastaken Loading…
1 of 4 tasks
1
feat: add dataclass config defaults infrastructure + GRPO POC (#2102) 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
#2270 opened Apr 15, 2026 by NolenLiang Contributor Loading…
3 tasks
6
feat: decouple IS correction level from GSPO policy ratio community-request needs-follow-up Issue needs follow-up
#2269 opened Apr 15, 2026 by bo-ke Loading…
1
Sglang Rollout Refactor community-request waiting-on-customer Waiting on the original author to respond
#2267 opened Apr 14, 2026 by xiuhu17 Loading…
27
add x-token alignment foundation and arrow dataset wiring community-request waiting-on-customer Waiting on the original author to respond
#2253 opened Apr 12, 2026 by avenkateshha Loading…
4 tasks
5
fix: preserve RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES to prevent NCCL NVSwitch bugs community-request waiting-on-customer Waiting on the original author to respond
#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 needs-follow-up Issue needs follow-up
#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
33
fix: workaround for optimizer offload
#2239 opened Apr 9, 2026 by yuki-97 Contributor • Draft
1
infra: K8s GPU cluster setup with KAI scheduler, KubeRay, and JobSet CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2238 opened Apr 9, 2026 by terrykong Collaborator • Draft
7 of 8 tasks
23
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.