Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
189 Open 1,331 Closed
189 Open 1,331 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

[5/5] feat: off-policy distillation algorithm and worker integration community-request
#2351 opened Apr 27, 2026 by avenkateshha • Draft
1 of 4 tasks
1
[4/5] feat: CUDA IPC for teacher logits transfer community-request
#2350 opened Apr 27, 2026 by avenkateshha • Draft
1 of 4 tasks
1
[3/5] feat: cross-tokenizer distillation loss and multi-teacher aggregator community-request
#2349 opened Apr 27, 2026 by avenkateshha • Draft
1 of 4 tasks
1
[2/5] feat: cross-tokenizer collator, Arrow dataset, and eval datasets community-request
#2348 opened Apr 27, 2026 by avenkateshha Loading…
1 of 4 tasks
1
[1/5] feat: add TokenAligner and cross-tokenizer projection utilities community-request
#2347 opened Apr 27, 2026 by avenkateshha Loading…
1 of 4 tasks
1
docs: Perf page update for v0.6 Documentation Improvements or additions to documentation
#2346 opened Apr 27, 2026 by guyueh1 Contributor Loading…
4 tasks
1
ci: shard unit tests from 3 to 9 parallel jobs CI:L0 Run doctests and unit tests CI Relating to CI
#2345 opened Apr 26, 2026 by chtruong814 Contributor Loading…
4 tasks
4
ci: cuda13 build. Do Not Merge CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI
#2344 opened Apr 26, 2026 by chtruong814 Contributor • Draft
4 tasks
11
test: Fix oom for grpo-dapomath17k-dsv3-32n4g-megatron
#2342 opened Apr 25, 2026 by guyueh1 Contributor Loading…
4 tasks
1
perf: Benchmark tuning CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version) testing Related to testing
#2341 opened Apr 25, 2026 by guyueh1 Contributor Loading…
4 tasks
@guyueh1
4
docs: add NVIDIA-Nemotron-3-Super-120B-A12B to model support page Documentation Improvements or additions to documentation
#2340 opened Apr 25, 2026 by terrykong Collaborator Loading…
1
1
fix: Ensure code coverage report is uploaded CI:L1 Run doctests, unit tests, and functional tests CI Relating to CI
#2339 opened Apr 25, 2026 by chtruong814 Contributor Loading…
4 tasks
4
fix: fix the blocking env issue CI:L1 Run doctests, unit tests, and functional tests
#2335 opened Apr 24, 2026 by youngeunkwon0405 Contributor Loading…
4 tasks
@youngeunkwon0405
2
cp: perf: Improve deepseek perf into r0.6.0
#2334 opened Apr 24, 2026 by kajalj22 Contributor Loading…
1 task
1
chore: Enable cuda-13 build CI:L1 Run doctests, unit tests, and functional tests
#2332 opened Apr 24, 2026 by chtruong814 Contributor Loading…
4 tasks
14
feat(nrl-k8s): Kubernetes infrastructure and CLI tooling
#2330 opened Apr 24, 2026 by terrykong Collaborator Loading…
3 tasks
14
Support restoring from MLM/Mbridge pretrained checkpoints
#2329 opened Apr 23, 2026 by ashors1 Contributor • Draft
4 tasks
1
perf: Perf script for swe nano model
#2327 opened Apr 23, 2026 by guyueh1 Contributor Loading…
4 tasks
fix: preserve matched filenames in no-underscore-md hook community-request waiting-on-maintainers Waiting on maintainers to respond
#2326 opened Apr 23, 2026 by ooooo-create Loading…
1 of 4 tasks
2
refactor: update TypedDict to BaseModel (MasterConfig & ClippedPGLossConfig) CI:L1 Run doctests, unit tests, and functional tests
#2325 opened Apr 23, 2026 by yuki-97 Contributor • Draft
3
feat: disaggregated generation and NemoGym
#2321 opened Apr 23, 2026 by terrykong Collaborator • Draft
2 tasks
12
fix: enable TE FusedAdam for Qwen3.5 MoE & GLM-4.7-Flash automodel recipes CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2320 opened Apr 23, 2026 by zpqiu Contributor Loading…
4 tasks
4
refactor: async generation code refactoring CI:L1 Run doctests, unit tests, and functional tests
#2318 opened Apr 23, 2026 by youngeunkwon0405 Contributor Loading…
4 tasks
@youngeunkwon0405
12
feat: add Qwen3.5 CP support for MCore path CI:L1 Run doctests, unit tests, and functional tests
#2312 opened Apr 22, 2026 by zpqiu Contributor • Draft
4 tasks
3
feat: group tests and recipes by accelerator (h100/gb200) subdirectories Documentation Improvements or additions to documentation
#2303 opened Apr 21, 2026 by terrykong Collaborator Loading…
5 tasks
1
ProTip! no:milestone will show everything without a milestone.