-
Notifications
You must be signed in to change notification settings - Fork 487
Pull requests: NVIDIA-NeMo/RL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ci: Bump Megatron-Bridge to cd76e0c
CI:L1
Run doctests, unit tests, and functional tests
#3358
opened Jul 27, 2026 by
svcnvidia-nemo-ci
Contributor
Loading…
fix(refit): stream a parameter larger than the IPC staging buffer
CI:L1
Run doctests, unit tests, and functional tests
#3356
opened Jul 27, 2026 by
terrykong
Collaborator
Loading…
fix(ci): AUT-1086 authenticate docs Hub requests
CI:docs
Run doctest
CI
Relating to CI
#3354
opened Jul 26, 2026 by
svcnemo-autobot
Contributor
Loading…
fix: merge grouped-expert LoRA weights during DTensor refit
community-request
#3353
opened Jul 26, 2026 by
rahul-sarvam
Loading…
3 of 4 tasks
chore: update NCCL to 2.30.4 via uv override
CI:L2
Run doctests, unit tests, functional tests, and convergence tests
#3352
opened Jul 26, 2026 by
yfw
Contributor
Loading…
4 tasks
chore: Update to NCCL 2.30.4
CI:L2
Run doctests, unit tests, functional tests, and convergence tests
#3351
opened Jul 26, 2026 by
yfw
Contributor
Loading…
4 tasks
fix(vllm): apply the TCPStore port offset on the branch vLLM actually takes
#3350
opened Jul 26, 2026 by
terrykong
Collaborator
Loading…
3 of 4 tasks
fix(async_utils): only close event loop after worker thread stops
community-request
#3348
opened Jul 25, 2026 by
andrewwhitecdw
Loading…
feat(mpo): add Nemotron Omni Nano and Super training
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
#3345
opened Jul 25, 2026 by
jinglinglingling
Contributor
•
Draft
4 of 6 tasks
chore: Bump Gym
CI:L1
Run doctests, unit tests, and functional tests
#3343
opened Jul 25, 2026 by
yfw
Contributor
Loading…
4 tasks
fix: reserve MOPD teacher clusters before Gym startup
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#3340
opened Jul 24, 2026 by
yfw
Contributor
Loading…
4 tasks
lora 2
community-request
Documentation
Improvements or additions to documentation
waiting-on-maintainers
Waiting on maintainers to respond
#3338
opened Jul 24, 2026 by
xrsrke
Loading…
4 tasks
[DO NOT MERGE] NCCL grow API demo
#3334
opened Jul 24, 2026 by
youngeunkwon0405
Contributor
Loading…
4 tasks
feat: standardize mcore generation config defaults and expose cuda_gr…
CI:L1
Run doctests, unit tests, and functional tests
#3331
opened Jul 23, 2026 by
shanmugamr1992
Contributor
Loading…
4 tasks
feat(sglang): add end-to-end training and refit integration
Documentation
Improvements or additions to documentation
feat(tq): train prefetch microbatches nccl
#3328
opened Jul 23, 2026 by
zyzhou5
Contributor
Loading…
4 tasks
Multimodal nemo gym compatible grpo pipeline
#3325
opened Jul 23, 2026 by
rohitrango
Contributor
Loading…
2 of 4 tasks
fix: harden multimodal Gym training lifecycle
#3324
opened Jul 23, 2026 by
JeffPengCoder
Loading…
6 tasks done
fix(eagle3): isolate draft grad clipping
#3323
opened Jul 23, 2026 by
yuekaizhang
Contributor
Loading…
fix: Megatron async checkpoint CUDA memory retention
CI:L1
Run doctests, unit tests, and functional tests
#3322
opened Jul 23, 2026 by
NolenLiang
Contributor
Loading…
3 tasks done
fix(ppo): enable DTensor value dynamic batching with equivalence coverage
CI:L1
Run doctests, unit tests, and functional tests
CI
Relating to CI
#3321
opened Jul 23, 2026 by
fujial-code
Contributor
Loading…
feat: support sequence packing and context parallelism for DTensor value models
CI:L1
Run doctests, unit tests, and functional tests
CI
Relating to CI
#3320
opened Jul 23, 2026 by
fujial-code
Contributor
Loading…
perf(loss): avoid full-vocab student log-softmax in same-vocab top-k KD
community-request
waiting-on-maintainers
Waiting on maintainers to respond
#3314
opened Jul 22, 2026 by
tianyi-zhang-02
Contributor
Loading…
3 tasks done
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.