VeRL-Omni v0.2.0: Faster Diffusion RL and Stable Omni Training

Following our May announcement of VeRL-Omni, v0.2.0 establishes a stronger foundation for production-grade omni-modal reinforcement learning. This release improves the training stack across rollout performance, model integration, reward support, hardware coverage, and documentation, with two changes carrying the most impact: Faster diffusion RL, centered on higher-throughput Qwen-Image FlowGRPO rollout via vLLM-Omni and verl V1 trainer support. Stable omni training, built around the omni V1 trainer, reusable model adapters, FSDP2, and vLLM-Omni rollout. 1. Faster Diffusion RL Diffusion RL is expensive, but not in the same way as autoregressive language-model RL. A single rollout carries many denoising steps, large latent tensors, prompt embeddings, optional classifier-free guidance, reward-model scoring, old-log-prob recomputation, and policy-weight synchronization. For Qwen-Image FlowGRPO, there is no single villain in the profile. Step time is shaped by rollout generation, old-log-prob computation, reward scoring,…