[BREAKING][reward] refactor: remove reward model worker code and invo… #4079
e2e_ppo_trainer_megatron_vllm_2.yml
on: push
setup
10s
e2e_ppo_trainer_megatron-moe-expert-parallel
19m 19s
e2e_ppo_trainer_fsdp_vllm
21m 37s
e2e_ppo_trainer_fsdp-qwen2_5vl-3b
19m 24s
cleanup
5s