Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
279 Open 1,640 Closed
279 Open 1,640 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(megatron): add large-scale MoE tuning knobs and longer PG timeout community-request
#2866 opened Jun 18, 2026 by dafu-wu Loading…
1 of 4 tasks
1
fix: tokenize system-led conversations for templates requiring a user turn community-request
#2864 opened Jun 17, 2026 by bzantium Loading…
3 of 4 tasks
1
1
feat: add NCCL timeout config, stale ZMQ socket cleanup, OmegaConfig resolvers community-request
#2862 opened Jun 17, 2026 by puneeshkhanna Loading…
1 of 4 tasks
1
fix(logger): summarize list-valued metrics to avoid MLflow key explosion community-request
#2861 opened Jun 17, 2026 by mrm-196 Contributor Loading…
3 of 4 tasks
1
ci: Bump Megatron-Bridge to 6e8c6bb CI:L1 Run doctests, unit tests, and functional tests
#2860 opened Jun 17, 2026 by svcnvidia-nemo-ci Contributor Loading…
3
fix(data): stabilize multi-turn chat chunking and tokenization CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2856 opened Jun 17, 2026 by jinglinglingling Contributor Loading…
4
ci: Add super nightly tests Documentation Improvements or additions to documentation
#2855 opened Jun 16, 2026 by ashors1 Contributor • Draft
4 tasks
2
docs(xtoken): X-Token distillation guide and README updates Documentation Improvements or additions to documentation
#2854 opened Jun 16, 2026 by avenkateshha Contributor Loading…
1
test: add vLLM HTTP logprobs contract test for NeMo-Gym capture CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2845 opened Jun 16, 2026 by ananthsub Contributor Loading…
4
feat: add vLLM prefix cache and preemption metrics community-request
#2843 opened Jun 16, 2026 by puneeshkhanna Loading…
1 of 4 tasks
2
feat(ppo): Megatron value-model sequence packing + context parallelism
#2839 opened Jun 16, 2026 by bg51717 Contributor • Draft
3 of 4 tasks
1
1
test(data_plane): session-scope mooncake fixtures CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2838 opened Jun 16, 2026 by ZhiyuLi-Nvidia Contributor Loading…
2
feat: Support for dtensor ppo CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2837 opened Jun 16, 2026 by fujial-code • Draft
1
14
feat: Support Chunked Linear Fusion for GRPO community-request Documentation Improvements or additions to documentation
#2833 opened Jun 16, 2026 by pengdurice Contributor Loading…
4 tasks done
11
ci: forward SANDBOX_CONTAINER/COMMAND/ENV_VARS to ray.sub
#2832 opened Jun 16, 2026 by kajalj22 Contributor • Draft
3 tasks
1
Asyncrl/sc sync weights
#2831 opened Jun 16, 2026 by mehraakash Loading…
4 tasks
1
ci: List bundled codecs
#2830 opened Jun 15, 2026 by kajalj22 Contributor • Draft
1 task
1
feat: super-v3 recipe and docs CI:L0 Run doctests and unit tests Documentation Improvements or additions to documentation super-v3
#2829 opened Jun 15, 2026 by macandro96 Contributor Loading…
4 tasks
5
feat: async checkpointing for Megatron policy workers CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2828 opened Jun 15, 2026 by ananthsub Contributor Loading…
2 of 4 tasks
3
perf: reduce srun overhead in ray.sub and gate driver on sandbox readiness CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2827 opened Jun 15, 2026 by ananthsub Contributor Loading…
4 tasks
2
feat: video + audio understanding GRPO training recipe CI:L1 Run doctests, unit tests, and functional tests Documentation Improvements or additions to documentation
#2823 opened Jun 15, 2026 by yuekaizhang Contributor Loading…
7
fix: avoid duplicating assistant content in multi-turn reasoning templates community-request waiting-on-maintainers Waiting on maintainers to respond
#2822 opened Jun 15, 2026 by bzantium Loading…
3 of 4 tasks
1
1
feat: single controller (w/o sync_weight)
#2819 opened Jun 15, 2026 by yuki-97 Contributor • Draft
1
feat: full Kubernetes multi-node support (Kubeflow PyTorchJob + KubeRay) community-request Documentation Improvements or additions to documentation waiting-on-maintainers Waiting on maintainers to respond
#2818 opened Jun 15, 2026 by dafu-wu Loading…
1
feat: NCCL-Xfer refit merge PR CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version) Performance Related to improving performance
#2808 opened Jun 15, 2026 by youngeunkwon0405 Contributor Loading…
4 tasks
@youngeunkwon0405
11
ProTip! Type g i on any issue or pull request to go back to the issue listing page.