VeRL-Omni v0.2.0: Faster Diffusion RL and Stable Omni Training
·9 min read
A release focused on higher-throughput diffusion rollout, reusable omni adapters, and broader recipe coverage.
#rlhf
2 posts
Menu
Theme
2 posts
A release focused on higher-throughput diffusion rollout, reusable omni adapters, and broader recipe coverage.
How VeRL-Omni extends verl with vLLM-Omni for reinforcement learning post-training of diffusion and multimodal generative models, including efficient rollouts, reward inference, trainers, hardware support, and recipes.