# vLLM Semantic Router and AMD release Vela 3.0 span-extraction models

> Original title: Great work from the vLLM Semantic Router, KR Labs, and @AMD teams on Vela 3.0!

- Source: vLLM
- Published: 2026-10-28T13:11:40.000Z
- Bad Influence: https://badinfluence.news/items/tilspd1jy99k2z76gqwtotrrf
- Original: https://x.com/vllm_project/status/2115431304896696391

## Summary

vLLM Semantic Router, KR Labs, and AMD released Vela 3.0, six open models from 0.3B to 27B parameters that return routing decisions and extracted spans in one call. The 380M model ranks first on the Decision Index among models up to 500M parameters, according to the post by Xunzhuo Liu. The collection is available on Hugging Face.

## Post

Great work from the vLLM Semantic Router, KR Labs, and @AMD teams on Vela 3.0!
Routing decisions and span extraction in one call, with six open models from 0.3B to 27B. More flexibility in what the router can detect and how small it can run.

## Quoted post @XunzhuoLiu

> Introducing Vela 3.0 📡 Name it. Vela finds it.
> 
> Six open models (0.3B–27B): decisions + the spans you name. One call.
> 
> ⚡ 380M: #1 Decision Index ≤500M
> 🎯 Beats GPT-5-mini at zero-shot classification
> 🔍 18 ms per span question
> 
> 🤗 https://huggingface.co/collections/vllm-sr/vela-30
> 
> #Jev #Decison

https://x.com/XunzhuoLiu/status/2115426759013491002