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
686 workflow runs
686 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix: dpo mistral nightly needs more time (#1225) Create PR to main with cherry-pick from release #486: Commit 0dca729 pushed by chtruong814
21s main
main
21s
fix: invalid time for fp8 grpo test 300 -> 240 minutes (#1220) Create PR to main with cherry-pick from release #485: Commit 5166d74 pushed by terrykong
9s main
main
9s
fix: Handle missing prompts in math HF data processor and add regress… Create PR to main with cherry-pick from release #484: Commit 4528931 pushed by terrykong
9s main
main
9s
fix: Reduce memory usage of gradient norm computation (#1138) Create PR to main with cherry-pick from release #483: Commit 1b96b45 pushed by terrykong
10s main
main
10s
test: add bisect-script.sh to help bisect CI tests (#1215) Create PR to main with cherry-pick from release #482: Commit 2570489 pushed by terrykong
12s main
main
12s
feat: FP8 Training in Megatron Path (#971) Create PR to main with cherry-pick from release #481: Commit 16e08cd pushed by terrykong
14s main
main
14s
feat: Update mbridge with cache support (#1187) Create PR to main with cherry-pick from release #480: Commit f521459 pushed by terrykong
14s main
main
14s
chore: remove deprecated --dashboard-grpc-port from ray.sub (#1209) Create PR to main with cherry-pick from release #479: Commit 9cc8c9f pushed by terrykong
11s main
main
11s
feat: Support passing in tool calls with OpenAI chat format when doin… Create PR to main with cherry-pick from release #478: Commit 6fe56b0 pushed by terrykong
11s main
main
11s
ci: Add status badge and prevent merging if no tests ran (#1192) Create PR to main with cherry-pick from release #477: Commit c01f9d7 pushed by chtruong814
9s main
main
9s
feat: support swanlab logger (#923) Create PR to main with cherry-pick from release #476: Commit 79b7a87 pushed by terrykong
11s main
main
11s
fix: minimize llama-super grpo config (#1206) Create PR to main with cherry-pick from release #475: Commit e60c4d9 pushed by terrykong
14s main
main
14s
feat: add config_cli.py and refactor configs + config pre-commit (#1024) Create PR to main with cherry-pick from release #474: Commit 32faafa pushed by terrykong
13s main
main
13s
feat: add support for nemotron-nas with custom plan. (#1180) Create PR to main with cherry-pick from release #473: Commit 56a6225 pushed by terrykong
11s main
main
11s
chore: patch KL loss to prevent nans (#876) Create PR to main with cherry-pick from release #472: Commit 7aa7071 pushed by parthchadha
12s main
main
12s
fix: can't find transformers_modules error for moonlight (#1124) Create PR to main with cherry-pick from release #471: Commit a579137 pushed by terrykong
11s main
main
11s
fix: Run crash on get_latest_checkpoint (#1168) Create PR to main with cherry-pick from release #470: Commit 38f0543 pushed by terrykong
11s main
main
11s
docs: Restructure README with backend-specific quick start and setup … Create PR to main with cherry-pick from release #469: Commit e22a340 pushed by terrykong
11s main
main
11s
docs: guide for sliding puzzle example (#961) Create PR to main with cherry-pick from release #468: Commit 63439ac pushed by terrykong
13s main
main
13s
chore: Delete .github/ISSUE_TEMPLATE directory (#1194) Create PR to main with cherry-pick from release #467: Commit a9ff45c pushed by terrykong
12s main
main
12s
fix: A fix in megatron YARN module for memory leak (#1163) Create PR to main with cherry-pick from release #466: Commit 66099f5 pushed by terrykong
9s main
main
9s
fix: Add check for world size and parallelism enabled (#1190) Create PR to main with cherry-pick from release #465: Commit 051c2f7 pushed by terrykong
13s main
main
13s
feat: support chat_template_kwargs in tokenizer config (#1165) Create PR to main with cherry-pick from release #464: Commit 64ee0d0 pushed by terrykong
13s main
main
13s
perf: Add a field in SFT data config to modify num_workers for loadin… Create PR to main with cherry-pick from release #463: Commit cde2acd pushed by terrykong
12s main
main
12s
feat: add async RL support (#1098) Create PR to main with cherry-pick from release #462: Commit 42aa41b pushed by terrykong
13s main
main
13s