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
687 workflow runs
687 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix: improve port selection and exiting early from ray.sub (#272) Create PR to main with cherry-pick from release #112: Commit 1363dba pushed by github-merge-queue bot
16s main
main
16s
docs: Correcting build issues and CI (#270) Create PR to main with cherry-pick from release #111: Commit 044f385 pushed by github-merge-queue bot
14s main
main
14s
feat: Updated Name to NeMo RL (#265) Create PR to main with cherry-pick from release #110: Commit 0fae6bc pushed by github-merge-queue bot
34s main
main
34s
fix: add bibtex entry (#273) Create PR to main with cherry-pick from release #109: Commit 34cae3a pushed by github-merge-queue bot
15s main
main
15s
docs: instruct users to git clone before beginning (#257) Create PR to main with cherry-pick from release #108: Commit ee0d2c8 pushed by github-merge-queue bot
16s main
main
16s
feat: E2E multi-turn RL example with a sliding puzzle game (#242) Create PR to main with cherry-pick from release #107: Commit 09f5416 pushed by github-merge-queue bot
13s main
main
13s
chore: better logging when insufficient resources (#271) Create PR to main with cherry-pick from release #106: Commit 47e51d3 pushed by github-merge-queue bot
14s main
main
14s
fix: Update DPO and SFT configs to use dtensor (#256) Create PR to main with cherry-pick from release #105: Commit 98473c6 pushed by github-merge-queue bot
16s main
main
16s
fix: Fix fsdp1 grad clipping and log grad norm (#251) Create PR to main with cherry-pick from release #104: Commit 2558444 pushed by github-merge-queue bot
15s main
main
15s
docs: add qwen 32b instruction and add 0.3 planned features (#255) Create PR to main with cherry-pick from release #103: Commit c8f0a01 pushed by github-merge-queue bot
13s main
main
13s
fix: fix broken eval script (#253) Create PR to main with cherry-pick from release #102: Commit 0a5f31d pushed by github-merge-queue bot
15s main
main
15s
ci: L1 default and increase test time (#252) Create PR to main with cherry-pick from release #101: Commit 2f8a140 pushed by github-merge-queue bot
18s main
main
18s
fix: use find_tied_parameters api from HF for tied weight keys (#250) Create PR to main with cherry-pick from release #100: Commit 1c7cbd9 pushed by github-merge-queue bot
14s main
main
14s
fix: raise error if tied weights model is being trained with fsdp1 or… Create PR to main with cherry-pick from release #99: Commit 1788e4c pushed by github-merge-queue bot
12s main
main
12s
fix: Fix indent in dtensor policy (#248) Create PR to main with cherry-pick from release #98: Commit 1fa4c7a pushed by github-merge-queue bot
14s main
main
14s
feat: streaming each dtensor in refit (#176) Create PR to main with cherry-pick from release #97: Commit ed546ae pushed by github-merge-queue bot
14s main
main
14s
feat: Importance sampling trick (#174) Create PR to main with cherry-pick from release #96: Commit 5c62657 pushed by github-merge-queue bot
16s main
main
16s
feat: Add support for multi-turn generations and RL (tools, games, et… Create PR to main with cherry-pick from release #95: Commit deaece6 pushed by github-merge-queue bot
16s main
main
16s
fix: Speed up DPO functional test (#241) Create PR to main with cherry-pick from release #94: Commit 1245c50 pushed by github-merge-queue bot
16s main
main
16s
fix: Move ray worker port range start from 20001 to 53001 (#235) Create PR to main with cherry-pick from release #93: Commit af369a3 pushed by github-merge-queue bot
18s main
main
18s
feat: Support multi-epoch training in SFT (#177) Create PR to main with cherry-pick from release #92: Commit 756152c pushed by github-merge-queue bot
14s main
main
14s
feat: DPO (#180) Create PR to main with cherry-pick from release #91: Commit bbdd671 pushed by github-merge-queue bot
18s main
main
18s
ci: Remove external config from project (#200) Create PR to main with cherry-pick from release #90: Commit 88bc0fd pushed by github-merge-queue bot
15s main
main
15s
fix: skip vllm p2p check since its flaky (#238) Create PR to main with cherry-pick from release #89: Commit 4a2e126 pushed by github-merge-queue bot
19s main
main
19s
feat: FSDP2 SFT (#206) Create PR to main with cherry-pick from release #88: Commit 22af21c pushed by github-merge-queue bot
14s main
main
14s
ProTip! You can narrow down the results and go further in time using created:<2025-04-21 or the other filters available.