Skip to content

[perf, fsdp, trainer] feat: Skip training for zero-advantage responses to speed up RL. #13091

[perf, fsdp, trainer] feat: Skip training for zero-advantage responses to speed up RL.

[perf, fsdp, trainer] feat: Skip training for zero-advantage responses to speed up RL. #13091

This workflow is awaiting approval from a maintainer in #5838
Triggered via pull request April 1, 2026 17:43
Status Action required
Total duration
Artifacts
This workflow is awaiting approval from a maintainer in #5838

model.yml

on: pull_request
setup
setup
model_engine
model_engine
model_rmpad
model_rmpad
model_rmpad_fsdp2_unstable
model_rmpad_fsdp2_unstable
cleanup
cleanup
Fit to window
Zoom out
Zoom in