Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
555 Open 2,434 Closed
555 Open 2,434 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

fix(megatron): Handle MTP position_ids correctly CI:L1 Run doctests, unit tests, and functional tests
#4098 opened Sep 11, 2026 by tdene Contributor Loading…
4 tasks
10
feat: add fp32 LM head toggle
#4096 opened Sep 11, 2026 by guyueh1 Contributor • Draft
1
feat(trtllm): TRT-LLM prefill/decode disaggregation for GRPO rollouts
#4095 opened Sep 11, 2026 by shuyixiong Contributor • Draft
4 tasks
1
feat(gym): add actor checkpoint participant
#4093 opened Sep 10, 2026 by ananthsub Contributor • 2/2 • Draft
2
feat(gym): persist stable rollout attempt identity
#4092 opened Sep 10, 2026 by ananthsub Contributor • 1/2 • Draft
1
perf(data-plane): avoid local batch copies
#4091 opened Sep 10, 2026 by rohitrango Contributor Loading…
3 of 4 tasks
14
fix: capture inner vLLM TP-worker nsys traces for ALL ranks
#4090 opened Sep 10, 2026 by zswerth Contributor Loading…
4 tasks
1
fix: Truncation condition from hitting max tokens
#4089 opened Sep 10, 2026 by pjin-nvidia Contributor Loading…
1
fix: fail fast when training dataloaders yield zero batches community-request
#4087 opened Sep 10, 2026 by tildahh Loading…
4 tasks done
1
8
fix(megatron): synchronize parameters before inference refit CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#4086 opened Sep 10, 2026 by wdykas Contributor Loading…
4
chore: add local pre-commit check script CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#4084 opened Sep 10, 2026 by rohitrango Contributor Loading…
2
fix(routing_replay): Disable routing replay for OPD teachers
#4083 opened Sep 10, 2026 by pjin-nvidia Contributor Loading…
1
feat(data): add PackedTensor preprocessing modes Documentation Improvements or additions to documentation
#4082 opened Sep 10, 2026 by rohitrango Contributor Loading…
6 tasks done
1
fix(async): gate rollout batches on validation pause CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#4081 opened Sep 10, 2026 by jepio Contributor Loading…
3 of 4 tasks
3
build: bump vllm to 0.29.0 Documentation Improvements or additions to documentation
#4080 opened Sep 10, 2026 by yfw Contributor • Draft
1
fix(megatron): preserve HybridEP packed-input alignment Documentation Improvements or additions to documentation
#4079 opened Sep 10, 2026 by seonjinn Contributor • Draft
3
feat(grpo): train all Gym traces per logical rollout Documentation Improvements or additions to documentation
#4078 opened Sep 10, 2026 by esarafian Loading…
4 tasks done
7
fix(qwen3.5): freeze vision modules in text-only recipes
#4077 opened Sep 10, 2026 by seonjinn Contributor • Draft
3 of 4 tasks
1
ci: Bump Megatron-Bridge to 4386117 CI:L1 Run doctests, unit tests, and functional tests
#4075 opened Sep 10, 2026 by svcnvidia-nemo-ci Contributor Loading…
3
refactor(sc): unify capture retries and extract orchestration components CI:L1 Run doctests, unit tests, and functional tests Documentation Improvements or additions to documentation
#4073 opened Sep 10, 2026 by pthombre Contributor • 2/2 • Draft
3 of 4 tasks
1
perf(reassembler): batch group staging reads and expose fetch timings CI:L1 Run doctests, unit tests, and functional tests
#4072 opened Sep 10, 2026 by pthombre Contributor • 1/2 • Draft
3 of 4 tasks
1
1
feat: add Energon-owned SFT sequence packing 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
#4070 opened Sep 10, 2026 by rohitrango Contributor Loading…
33
feat(grpo): add Binary-TV DPPO training support
#4069 opened Sep 10, 2026 by guyueh1 Contributor Loading…
1
feat(sc): add per-environment rollout telemetry
#4068 opened Sep 9, 2026 by mehraakash Contributor • Draft
2
fix(sc): regenerate buffered prompts on resume
#4067 opened Sep 9, 2026 by mehraakash Contributor • Draft
2
ProTip! Exclude everything labeled bug with -label:bug.