[algo, doc] feat: trust region sequence masking - (1) k3 KL avg and (2) veto for max criterion #9505
This workflow is awaiting approval from a maintainer in #4544
Triggered via pull request
December 30, 2025 09:21
jiawei415
Status
Action required
Total duration
–
Artifacts
–
This workflow is awaiting approval from a maintainer in #4544
e2e_ascend.yml
on: pull_request
E2E Ascend testing for RL training scenarios of LLM models
E2E Ascend testing for RL training scenarios of VLM models
E2E Ascend testing for non-RL algorithm scenarios
E2E Ascend testing for recipes