Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
89 Open 960 Closed
89 Open 960 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

[don't merge] support multiple dataloader
#1698 opened Dec 24, 2025 by yuki-97 • Draft
feat: RL support for custom moe models in dtensor v2 CI:L1 Run doctests, unit tests, and functional tests
#1695 opened Dec 24, 2025 by hemildesai Loading…
@hemildesai
7
docs: Add doc for nano-v3 CI:docs Run doctest documentation Improvements or additions to documentation
#1694 opened Dec 24, 2025 by yfw Loading…
4 tasks
11
[don't merge] support multiple datasets for response dataset CI:L1 Run doctests, unit tests, and functional tests
#1691 opened Dec 23, 2025 by yuki-97 • Draft
fix: Fix DTensor slice crash after PyTorch 2.9 bump CI:L2 Run doctests, unit tests, functional tests, and convergence tests r0.5.0
#1689 opened Dec 23, 2025 by zpqiu Loading…
4 tasks
1
feat: Add SGLang rollout backend and tests community-request
#1674 opened Dec 21, 2025 by RolaoDenthu Loading…
4 tasks
10
Nano v3 lora
#1669 opened Dec 20, 2025 by arendu • Draft
4 tasks
fix: Add debug parameter to reduce verbose output community-request
#1664 opened Dec 19, 2025 by sahgerlad Loading…
1
refactor: Order node by IP in GRPO CI:L2 Run doctests, unit tests, functional tests, and convergence tests GB200
#1655 opened Dec 18, 2025 by guyueh1 Loading…
4 tasks
@guyueh1
7
feat: refactor mcore train/forward utilities
#1654 opened Dec 17, 2025 by ashors1 • Draft
4 tasks
chore: update Megatron-LM submodule to ed804b4
#1653 opened Dec 17, 2025 by yaoyu-33 Loading…
4 tasks
6
feat: refactor megatron data utils
#1651 opened Dec 17, 2025 by ashors1 • Draft
4 tasks
refactor: split train and val dataset in response dataset CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation
#1649 opened Dec 17, 2025 by yuki-97 Loading…
42
feat: refactor megatron init
#1646 opened Dec 17, 2025 by ashors1 • Draft
4 tasks
perf: Add DeepEP support to Megatron Policy CI:L2 Run doctests, unit tests, functional tests, and convergence tests
#1645 opened Dec 17, 2025 by parthmannan Loading…
4 tasks
8
tests: add nanov3 nightly/release tests
#1644 opened Dec 16, 2025 by terrykong • Draft
4 tasks
feat: Omni dataloader for HF models community-request
#1639 opened Dec 15, 2025 by yuanhangsu1986 Loading…
18
fix: split dtensorv1 vllm dependency CI:L1 Run doctests, unit tests, and functional tests
#1638 opened Dec 15, 2025 by yuki-97 Loading…
11
[feat]: added one-logger support for NeMo RL community-request
#1631 opened Dec 14, 2025 by therealnaveenkamal Loading…
1 of 4 tasks
31
feat: Megatron SFT LoRA CI:L1 Run doctests, unit tests, and functional tests documentation Improvements or additions to documentation r0.5.0
#1629 opened Dec 12, 2025 by arendu Loading…
4 tasks
12
feat: Add attention_backend config support for Megatron policy community-request
#1628 opened Dec 12, 2025 by sahgerlad Loading…
3
Add grpo-qwen3-30ba3b-4n8g-128k config to performance test suite.
#1623 opened Dec 11, 2025 by sfawzy-nv Loading…
4 tasks
3
fix: allow zero grad norm in dtensor policies for consistency with Megatron CI:L1 Run doctests, unit tests, and functional tests
#1618 opened Dec 9, 2025 by smahdavi4 Loading…
3
feat: Support for Ray spinup within Gym
#1613 opened Dec 9, 2025 by pjin-nvidia • Draft
4 tasks
feat: Support Ray Compiled Graph for SFT
#1612 opened Dec 9, 2025 by katec846 Loading…
5 of 10 tasks
33
ProTip! Add no:assignee to see everything that’s not assigned.