
vLLM Semantic Router releases Decision 3.0, open decision models that read images and video
The vLLM Semantic Router team published six Apache-2.0 d3 models, from 0.6B to 27B, that answer choice, yes/no and score questions about text, images and video in one pass. The 27B d3 tops the team’s own run of the Jev Decision Index at 64.7.




































