# VeRL-Omni v0.3.0 adds async multimodal RL training and makes V1 the default

> Original title: VeRL-Omni v0.3.0: Async Training and Broader Multimodal Post-Training

- Source: vLLM Blog
- Published: 2026-11-06T00:00:00.000Z
- Bad Influence: https://badinfluence.news/items/xyk2g9znvuxq54vt24lp250pm
- Original: https://vllm.ai/blog/2026-11-06-verl-omni-v0-3-0

## Summary

VeRL-Omni v0.3.0 extends asynchronous execution to more multimodal RL workloads and makes the V1 trainer the default. The release adds recipes for MiniMax H3 audio-video post-training and MiniCPM-o 4.5 GSPO, with some legacy paths requiring explicit configuration. In a single-node test, separate-async placement was about 9% slower per prompt on short answers and about 6.7% faster at 1024 tokens.

## Why it matters

The post gives per-prompt timing data for sync versus separate-async placement at several response lengths, useful for deciding which execution mode fits a workload.