-
Notifications
You must be signed in to change notification settings - Fork 274
Pull requests: NVIDIA-NeMo/RL
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ci: Switch to merge-commit CI
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
CI
Relating to CI
#2077
opened Mar 6, 2026 by
ko3n1g
Loading…
4 tasks
[WIP] support qwen-omni grpo training recipe
community-request
#2073
opened Mar 6, 2026 by
yuekaizhang
Loading…
6 tasks
feat: support GDPO (New)
CI:Lfast
Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2069
opened Mar 5, 2026 by
nbasyl
Loading…
4 tasks
tests: add megatron bump suite
CI:docs
Run doctest
#2068
opened Mar 5, 2026 by
terrykong
Loading…
4 tasks
feat(sft): add DataPrefetcher for background data preprocessing
community-request
#2064
opened Mar 4, 2026 by
dafu-wu
Loading…
4 tasks
Adding On-Policy Self-Distillation to Nemo-RL
community-request
#2063
opened Mar 4, 2026 by
Hoponga
Loading…
4 tasks
ci: Temp disable megatron lora grpo tests
CI:docs
Run doctest
#2062
opened Mar 4, 2026 by
chtruong814
Loading…
4 tasks
Vllm grpo experiments
documentation
Improvements or additions to documentation
#2059
opened Mar 4, 2026 by
shaunjoshi
Loading…
4 tasks
feat: add code generation evaluation with test-case-driven sandbox environment
community-request
#2056
opened Mar 3, 2026 by
brluobt
Loading…
5 of 6 tasks
feat: support top-p top-k in grpo
CI:L1
Run doctests, unit tests, and functional tests
#2053
opened Mar 3, 2026 by
yuki-97
Loading…
feat: Add YaRN rope scaling support on Magatron-Bridge
documentation
Improvements or additions to documentation
docs: add prerequisites, troubleshooting, and build verification for GRPO quickstart
community-request
documentation
Improvements or additions to documentation
#2051
opened Mar 3, 2026 by
brluobt
Loading…
3 tasks
chore: bumpup Megatron-Bridge submodule to main
CI:L2
Run doctests, unit tests, functional tests, and convergence tests
Run CICD
#2039
opened Mar 1, 2026 by
ZhiyuLi-Nvidia
Loading…
4 tasks
fp8 refit opt
Performance
Related to improving performance
#2037
opened Feb 28, 2026 by
Jianbing-D
•
Draft
4 tasks
feat: Add chunked linear ce loss function from hidden states
community-request
#2036
opened Feb 27, 2026 by
pengdurice
Loading…
3 of 4 tasks
chore: address deprecation warning for using a non-tuple sequence for multidimensional indexing
CI:L1
Run doctests, unit tests, and functional tests
feat: split validation statistics by task name
CI:L1
Run doctests, unit tests, and functional tests
documentation
Improvements or additions to documentation
#2019
opened Feb 24, 2026 by
yuki-97
Loading…
feat: adding wandb table log feature, showing concrete test samples
community-request
documentation
Improvements or additions to documentation
#2018
opened Feb 24, 2026 by
vinhngx
Loading…
4 tasks
ci: Enable GB200 runners
CI:L1
Run doctests, unit tests, and functional tests
CI
Relating to CI
#2017
opened Feb 24, 2026 by
chtruong814
Loading…
4 tasks
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.