- cispo_trainer
- data_preprocess
- generation
- gmpo_trainer
- gpg_trainer
- grpo_trainer
- gspo_trainer
- mtp_trainer
- otb_trainer
- ppo_trainer
- prefix_grouper
- ray
- reinforce_plus_plus_trainer
- remax_trainer
- rloo_trainer
- rollout_correction
- router_replay
- sapo_trainer
- sft
- sglang_multiturn
- skypilot
- slurm
- split_placement
- tuning
- tutorial