Skip to content

Pull requests: NVIDIA-NeMo/RL

New pull request New
265 Open 1,556 Closed
265 Open 1,556 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

ci: Bump Megatron-Bridge to 823b951 CI:L1 Run doctests, unit tests, and functional tests
#2735 opened Jun 7, 2026 by svcnvidia-nemo-ci Contributor Loading…
4
fix: fix grpo-gptoss-20b-8n8g-megatron CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2734 opened Jun 7, 2026 by yuki-97 Contributor Loading…
2
[TRAIN-8] Add end-to-end custom reward functions tutorial community-request Documentation Improvements or additions to documentation
#2733 opened Jun 7, 2026 by mkcash Loading…
1
1
fix: fix qwen3-235b deepseek-v3 h100 perf tests CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2703 opened Jun 5, 2026 by yuki-97 Contributor Loading…
5
feat(algorithms): SingleController streaming train_pump (split-API consumer) CI:L0 Run doctests and unit tests
#2700 opened Jun 5, 2026 by mehraakash Loading…
2 of 3 tasks
6
feat(policy): split-API train-step state machine on DTensor v1/v2 CI:L0 Run doctests and unit tests
#2692 opened Jun 4, 2026 by mehraakash Loading…
3 tasks
5
chore: bump Gym workspace to v0.3.0 CI:L1 Run doctests, unit tests, and functional tests
#2691 opened Jun 4, 2026 by kajalj22 Contributor Loading…
2 tasks
3
[DoNotMerge] Modularity/wire weight sync TransferQueue validation
#2690 opened Jun 4, 2026 by saumishr Contributor • Draft
4 tasks
1
test: guard the MXFP8 flashinfer trtllm-gen MoE fast path from silent regressions community-request waiting-on-maintainers Waiting on maintainers to respond
#2689 opened Jun 4, 2026 by puririshi98 Loading…
1
feat: add MiniMax M2.7 support CI:L1 Run doctests, unit tests, and functional tests
#2685 opened Jun 4, 2026 by jQizhang Contributor Loading…
3 of 4 tasks
5
feat(megatron): split-API train-step state machine on MegatronPolicyWorker CI:L0 Run doctests and unit tests
#2683 opened Jun 4, 2026 by mehraakash Loading…
4 tasks
5
feat: GDPO vs GRPO multi-reward example, collapse demo, and experiment skill
#2681 opened Jun 3, 2026 by anjalibshah Loading…
1
feat: configurable GDPO per-reward weights and multi-reward NeMo Gym bridge Documentation Improvements or additions to documentation
#2680 opened Jun 3, 2026 by anjalibshah Loading…
1
ci: bump _release_library.yml to v1.4.3 CI Relating to CI
#2678 opened Jun 3, 2026 by ko3n1g Contributor Loading…
1
feat: Enable tqdm configuration for vllm generation community-request waiting-on-customer Waiting on the original author to respond
#2677 opened Jun 3, 2026 by louisfaury Loading…
2 of 4 tasks
4
chore: bump _code_freeze workflow to v1.4.2 CI Relating to CI
#2675 opened Jun 3, 2026 by ko3n1g Contributor Loading…
1
Add nano_v3 vLLM reasoning parser plugin
#2673 opened Jun 2, 2026 by dpickem Loading…
4 tasks
2
feat: Add script to re-initialize near-zero HF embeddings Documentation Improvements or additions to documentation
#2671 opened Jun 2, 2026 by ashors1 Contributor Loading…
4 tasks
1
fix: Fix fp8 memory fragmentation
#2670 opened Jun 2, 2026 by ashors1 Contributor Loading…
4 tasks
1
5
fix: resolve qwen3.5-35ba3b megatron ep16 OOM via TP=2 (#2619)
#2668 opened Jun 2, 2026 by sharonyu-115 Contributor Loading…
4 tasks
2
chore: bump transfomrers 5.5 CI:L1 Run doctests, unit tests, and functional tests
#2667 opened Jun 2, 2026 by yuekaizhang Contributor Loading…
14
test(converters): add CLI entry-point coverage for all three converte… community-request waiting-on-customer Waiting on the original author to respond
#2666 opened Jun 2, 2026 by SakethKoona Loading…
3 of 4 tasks
8
fix(security): bump deps for CVE remediation (June 2026) CI:L1 Run doctests, unit tests, and functional tests
#2663 opened Jun 2, 2026 by kajalj22 Contributor • Draft
4 tasks
3
fix(nrl-k8s): remove SA impersonation from dev pod RBAC check CI:Lfast Runs a fast test suite and re-use nightly `main` container (but sync dependencies to PRs version)
#2655 opened Jun 1, 2026 by terrykong Collaborator Loading…
2 tasks done
3
refactor: refactor generation config CI:L1 Run doctests, unit tests, and functional tests Documentation Improvements or additions to documentation
#2653 opened Jun 1, 2026 by yuki-97 Contributor • Draft
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.