Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
77 Open 895 Closed
77 Open 895 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

chore: rename penguin -> nemo_gym and add the gym submodule
#1587 opened Dec 2, 2025 by terrykong Loading…
4 tasks
5
refactor: Introduce BasePolicyWorker CI Relating to CI documentation Improvements or additions to documentation
#1585 opened Dec 1, 2025 by ashors1 • Draft
4 tasks
2
docs: get started section documentation Improvements or additions to documentation
#1582 opened Dec 1, 2025 by lbliii • Draft
4 tasks
@lbliii
feat: add SGLang rollout backend, part1 [WIP]
#1580 opened Nov 30, 2025 by PrinsYin • Draft
4 tasks
3
fix: Fix Fp8 sequence padding for PP>1 case CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#1579 opened Nov 29, 2025 by guyueh1 Loading…
4 tasks
@guyueh1
1
feat: Support top-p and top-k CI:L1 Run doctests, unit tests, and functional tests
#1578 opened Nov 27, 2025 by zhandaz Loading…
3 of 4 tasks
21
feat: genrm rlhf
#1576 opened Nov 27, 2025 by yfw • Draft
4 tasks
Update megatron bridge and megatron-core
#1568 opened Nov 25, 2025 by yaoyu-33 Loading…
4 tasks
6
feat: plot vllm internal metrics to the wandb log CI:L1 Run doctests, unit tests, and functional tests ease of use
#1567 opened Nov 25, 2025 by youngeunkwon0405 Loading…
4 tasks
@youngeunkwon0405
14
chore: Bump vllm to 0.11.2, torch to 2.9, transformers to 4.57.1 CI:L1 Run doctests, unit tests, and functional tests
#1563 opened Nov 24, 2025 by yfw Loading…
4 tasks
13
fix: fix Dtensor sharding error when bump up pytorch version
#1557 opened Nov 21, 2025 by ZhiyuLi-Nvidia Loading…
4 tasks
4
feat: LoRA SFT support for DTensorV2 path CI:L1 Run doctests, unit tests, and functional tests
#1556 opened Nov 21, 2025 by samodi-nv Loading…
2 tasks done
@samodi-nv
19
fix: remove sft-qwen2.5-fsdp2tp8sp from nighlies CI:L0 Run doctests and unit tests
#1555 opened Nov 20, 2025 by ahmadki Loading…
2
fix: add H200 TFLOPS CI:L0 Run doctests and unit tests community-request
#1543 opened Nov 19, 2025 by clumsy Loading…
4 tasks done
6
feat: refactor dtensor policy v2 into core modular functions
#1542 opened Nov 19, 2025 by hemildesai • Draft
4 tasks
fix: Use Float16Module even when defer_fp32_logits=True CI:L1 Run doctests, unit tests, and functional tests
#1537 opened Nov 18, 2025 by yfw Loading…
4 tasks
2
feat: Support qwen3-next, mcore path
#1530 opened Nov 17, 2025 by ahmadki Loading…
1 task
15
feat: force on-policy ratio to 1 CI:L1 Run doctests, unit tests, and functional tests
#1529 opened Nov 17, 2025 by yfw Loading…
4 tasks
2
feat: RL sampler [WIP]
#1522 opened Nov 14, 2025 by pjin-nvidia • Draft
4 tasks
feat: Add moe load balancing metrics CI:L1 Run doctests, unit tests, and functional tests
#1520 opened Nov 13, 2025 by yfw Loading…
4 tasks
4
feat: Automodel init for DTensorPolicyV2 CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#1509 opened Nov 12, 2025 by adil-a Loading…
14
refactor: refactor env and data processor & add nemotron super 49b recipes CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#1506 opened Nov 11, 2025 by yuki-97 Loading…
68
feat: pipeline-rl style # of inflight prompt regulation CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#1499 opened Nov 10, 2025 by youngeunkwon0405 Loading…
4 tasks
@youngeunkwon0405
11
fix: Support vLLM DP+EP in async engine via Ray-level data parallelism community-request
#1495 opened Nov 10, 2025 by clumsy Loading…
4 tasks done
10
feat: allow uv-less execution and fingerprint the environment CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI documentation Improvements or additions to documentation
#1491 opened Nov 9, 2025 by terrykong Loading…
1
12
ProTip! Follow long discussions with comments:>50.