Skip to content

Actions: NVIDIA-NeMo/RL

Actions

Create PR to main with cherry-pick from release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
cherry-pick-release-commit.yml
647 workflow runs
647 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix: Fix DTensor slice crash after PyTorch 2.9 bump (#1689) Create PR to main with cherry-pick from release #647: Commit c8d6569 pushed by terrykong
18s main
main
18s
feat: Support prefetching of specific envs (#1692) Create PR to main with cherry-pick from release #646: Commit f017fd8 pushed by terrykong
11s main
main
11s
feat: Add Nemotron‑3 Nano 30B A3B BF16 SFT nightly tests (FSDP2, +LoR… Create PR to main with cherry-pick from release #645: Commit 433eaa1 pushed by terrykong
18s main
main
18s
fix: grad norm calculation for dtensor v2 (#1693) Create PR to main with cherry-pick from release #644: Commit ffca73e pushed by terrykong
15s main
main
15s
feat: DTensorPolicyV2 GPT-OSS SFT support (#1470) Create PR to main with cherry-pick from release #643: Commit 669e70c pushed by yuki-97
17s main
main
17s
feat: add dapo recipe and test (#1617) Create PR to main with cherry-pick from release #642: Commit 56e8fcb pushed by terrykong
19s main
main
19s
fix: Fix crash when using activation_checkpointing (#1676) Create PR to main with cherry-pick from release #641: Commit 02d5142 pushed by terrykong
13s main
main
13s
fix: Fix fp8 after vllm v0.11.2 bump (#1660) Create PR to main with cherry-pick from release #640: Commit b238e41 pushed by terrykong
18s main
main
18s
test: Perf recipe for v0.5 (#1667) Create PR to main with cherry-pick from release #639: Commit fab6234 pushed by terrykong
15s main
main
15s
fix: Fix Fp8 sequence padding for PP>1 case (#1579) Create PR to main with cherry-pick from release #638: Commit d0651dd pushed by terrykong
13s main
main
13s
fix: Fix crash when using cp in dtensor path (#1663) Create PR to main with cherry-pick from release #637: Commit 91658c8 pushed by terrykong
18s main
main
18s
fix: Handle disabled validation in SFT training (#1611) Create PR to main with cherry-pick from release #636: Commit 4794ca7 pushed by terrykong
12s main
main
12s
fix: Support datasets saved with save_to_disk in ResponseDataset (#1610) Create PR to main with cherry-pick from release #635: Commit 48dbb37 pushed by terrykong
12s main
main
12s
chore: Bump vllm to 0.11.2, torch to 2.9, transformers to 4.57.1 (#1563) Create PR to main with cherry-pick from release #634: Commit 5bf56a9 pushed by terrykong
10s main
main
10s
feat: Add GPT-OSS support via mcore (#1452) Create PR to main with cherry-pick from release #633: Commit 441f745 pushed by terrykong
13s main
main
13s
perf: Add qwen3 30b-a3b async-8-off recipe (#1642) Create PR to main with cherry-pick from release #632: Commit 7dd9a01 pushed by terrykong
11s main
main
11s
feat: Necessary changes for Gym GRPO tutorial (#1630) Create PR to main with cherry-pick from release #631: Commit 0bddd47 pushed by terrykong
11s main
main
11s
feat: add support from building images using vllm from private repos … Create PR to main with cherry-pick from release #630: Commit df01ca7 pushed by terrykong
9s main
main
9s
chore: fix grpo functional test metric (#1643) Create PR to main with cherry-pick from release #629: Commit 52cebdf pushed by terrykong
10s main
main
10s
docs: Revise news section for nemotron v3 and DAPO algorithm support … Create PR to main with cherry-pick from release #628: Commit d4fffe0 pushed by terrykong
12s main
main
12s
chore: Enable LoRA Nightly Test (#1634) Create PR to main with cherry-pick from release #627: Commit a010564 pushed by terrykong
13s main
main
13s
fix: Set use_flashinfer_fused_rope to False (#1636) Create PR to main with cherry-pick from release #626: Commit 363165a pushed by terrykong
14s main
main
14s
docs: Add SkyRL to inspired libraries list (#1632) Create PR to main with cherry-pick from release #625: Commit 995efaa pushed by terrykong
11s main
main
11s
chore: update megatron dev (11/21/2025) / mbridge (11/28/2025) (#1568) Create PR to main with cherry-pick from release #624: Commit 5d04b36 pushed by terrykong
10s main
main
10s
fix: Sort rollout outputs to match inputs order + gym bump (#1627) Create PR to main with cherry-pick from release #623: Commit 5e3c0e2 pushed by terrykong
13s main
main
13s