Skip to content

Add OPSD (On-Policy Distillation) training example#1002

Open
delock wants to merge 2 commits into
masterfrom
gma/opsd
Open

Add OPSD (On-Policy Distillation) training example#1002
delock wants to merge 2 commits into
masterfrom
gma/opsd

Use ROLLOUT_VISIBLE_DEVICE env var for vLLM GPU placement; rename vll…

6b8f584
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Jul 2, 2026 in 1s

DCO

All commits are signed off!