Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
55 Open 539 Closed
55 Open 539 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: address double bos in eval task
#962 opened Aug 21, 2025 by ZhiyuLi-Nvidia Loading…
2 of 4 tasks
docs: guide for sliding puzzle example documentation Improvements or additions to documentation
#961 opened Aug 21, 2025 by slikhite-1 Loading…
test: add non-colocated release test
#960 opened Aug 21, 2025 by yuki-97 • Draft
feat: GRPO example for Qwen3 32b context length=128k
#957 opened Aug 20, 2025 by soodoshll Loading…
4 tasks
@soodoshll
1
fix: fix scheduler decay steps with megatron backend
#939 opened Aug 19, 2025 by ashors1 Loading…
4 tasks
fix: fix temperature-related issues in the DTensor path
#935 opened Aug 18, 2025 by zhandaz Loading…
2
@zhandaz
11
ci: Update community bot to add issues to shared project CI Relating to CI
#931 opened Aug 16, 2025 by chtruong814 Loading…
4 tasks
fix: memory optimizations for Nemotron12B 12k seqlen DPO training CI:L1 Run doctests, unit tests, and functional tests
#926 opened Aug 14, 2025 by ybgao-nvidia Loading…
4 tasks
1
@ybgao-nvidia
25
feat: support swanlab logger CI:docs Run doctest documentation Improvements or additions to documentation
#923 opened Aug 14, 2025 by terrykong Loading…
6
feat: multi-turn search R1 example
#914 opened Aug 13, 2025 by soodoshll Loading…
4 tasks
@soodoshll
18
Set submodule check to use pull_request_target CI Relating to CI
#913 opened Aug 13, 2025 by chtruong814 Loading…
4 tasks
feat: add tp_comm_bootstrap_backend,tp_comm_overlap as mcore backend …
#912 opened Aug 13, 2025 by terrykong • Draft
4 tasks
feat: Migration from NeMo Tron to Megatron Bridge
#905 opened Aug 12, 2025 by yaoyu-33 Loading…
4 tasks
13
feat: Enable global post process and metrics
#899 opened Aug 12, 2025 by jubick1337 Loading…
4 tasks
feat: Improve DCP to HF checkpoint conversion
#892 opened Aug 11, 2025 by 1ytic Loading…
feat: LLaDA Model Support enhancement New feature or request
#878 opened Aug 8, 2025 by trias702 Loading…
2 of 4 tasks
chore: patch KL loss to prevent nans
#876 opened Aug 8, 2025 by rohitrango Loading…
Bxyu test
#872 opened Aug 8, 2025 by bxyu-nvidia • Draft
4 tasks
feat: GSPO
#859 opened Aug 6, 2025 by pjin-nvidia Loading…
4 tasks
13
chore: output safetensors + remove logger before backend is ready
#852 opened Aug 6, 2025 by anubhutivyas Loading…
4 tasks
feat: async grpo training
#851 opened Aug 5, 2025 by parthchadha • Draft
4 tasks
2
fix: Fix megatron checkpoint loading during sft
#836 opened Aug 4, 2025 by yfw Loading…
4 tasks
feat: Add guided decoding passthrough to vLLM
#827 opened Aug 3, 2025 by ybgao-nvidia Loading…
4 tasks
1
@ybgao-nvidia
27
feat: support loading jinja templates from file documentation Improvements or additions to documentation
#826 opened Aug 2, 2025 by keatonelvins Loading…
4 tasks done
fix: crash when sequence packing is enabled for gemma 1b. bug Something isn't working CI:L1 Run doctests, unit tests, and functional tests
#809 opened Jul 31, 2025 by joyang-nv Loading…
4 tasks
1
@joyang-nv
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.