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
658 workflow runs
658 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

docs: add v0.4 news and minor touch up to front page readme (#1268) Create PR to main with cherry-pick from release #608: Commit db1f522 pushed by terrykong
17s main
main
17s
feat: plot vllm internal metrics to the wandb log (#1567) Create PR to main with cherry-pick from release #607: Commit edd5e7a pushed by terrykong
12s main
main
12s
fix: Use Float16Module even when defer_fp32_logits=True (#1537) Create PR to main with cherry-pick from release #606: Commit a0755eb pushed by terrykong
14s main
main
14s
feat: KV cache quantization support in fp8 rollout in GRPO (#1212) Create PR to main with cherry-pick from release #605: Commit 40e7040 pushed by terrykong
15s main
main
15s
docs: Update nvidia-sphinx-theme (#1584) Create PR to main with cherry-pick from release #604: Commit 3817189 pushed by terrykong
13s main
main
13s
docs: Create performance-summary.md for NeMo RL (#1560) Create PR to main with cherry-pick from release #603: Commit cff17f8 pushed by terrykong
11s main
main
11s
build: Use dynamic engine for generate. (#1502) Create PR to main with cherry-pick from release #602: Commit 66d80e6 pushed by terrykong
11s main
main
11s
fix: Fix the sequence padding for FP8 case (#1569) Create PR to main with cherry-pick from release #601: Commit 25ff3f6 pushed by terrykong
16s main
main
16s
feat: Fp8 moe rollout (#1446) Create PR to main with cherry-pick from release #600: Commit b772e48 pushed by terrykong
12s main
main
12s
chore: Improve checkpoint loading error messages with common issue an… Create PR to main with cherry-pick from release #599: Commit fa379ff pushed by terrykong
15s main
main
15s
feat: per-worker active/idle timeline + IFB size logging (#1534) Create PR to main with cherry-pick from release #598: Commit 6639a40 pushed by terrykong
13s main
main
13s
perf: [Perf script] QWEN3 30B-A3B tensor_parallel_size from 4 to 2 (#… Create PR to main with cherry-pick from release #597: Commit 5f6cfc7 pushed by terrykong
12s main
main
12s
docs: remove doc pyproject toml (#1561) Create PR to main with cherry-pick from release #596: Commit 9a84cc2 pushed by terrykong
11s main
main
11s
chore: add a research template project (#1278) Create PR to main with cherry-pick from release #595: Commit 4a59436 pushed by terrykong
11s main
main
11s
fix: removed sliding_window_overwrite (#1541) Create PR to main with cherry-pick from release #594: Commit 5e25142 pushed by terrykong
13s main
main
13s
perf: perf script change for qwen30b-a3b (#1526) Create PR to main with cherry-pick from release #593: Commit 1c371a9 pushed by terrykong
12s main
main
12s
build: Update docker file to include OSS NOTICES.txt (#1544) Create PR to main with cherry-pick from release #592: Commit 08534fe pushed by terrykong
19s main
main
19s
fix: honor mlflow server artifact_location (#1536) (#1538) Create PR to main with cherry-pick from release #591: Commit 7257c30 pushed by terrykong
12s main
main
12s
fix: Update Penguin tests to use renamed resource server (#1540) Create PR to main with cherry-pick from release #590: Commit 55dc433 pushed by terrykong
9m 31s main
main
9m 31s
feat: Support for nano-v2 (#1514) Create PR to main with cherry-pick from release #589: Commit c32778d pushed by terrykong
11s main
main
11s
fix: Incompatible configuration between reward normalization and the … Create PR to main with cherry-pick from release #588: Commit 775fc34 pushed by terrykong
15s main
main
15s
docs: Refactor Home Page and New About Section (#1338) Create PR to main with cherry-pick from release #587: Commit 74b9b17 pushed by terrykong
11s main
main
11s
fix: improve local eval config and doc (#1528) Create PR to main with cherry-pick from release #586: Commit 45f5ce6 pushed by terrykong
10s main
main
10s
fix: fixing the sequence parallel related issue in mcore path (#1487) Create PR to main with cherry-pick from release #585: Commit 6fc917f pushed by terrykong
13s main
main
13s
feat: improve non-colocated startup by starting policy and vllm in pa… Create PR to main with cherry-pick from release #584: Commit b3a7892 pushed by terrykong
13s main
main
13s