Featured

Decision 3.0 on Apple Silicon: Text, Image and Video Decisions on a Mac

Oct 11, 20266 min read

d3-lite, d3-nano and d3-mini converted to Core ML: triage 1,000 pull requests at 0.12 s each, drive a real website and watch live video, all on one Mac.

routing

Decision Models Need a Router, Too

Oct 10, 20269 min read

vela

Vela 2.0: Open Foundation Routing Models

Oct 6, 202624 min read

evaluation

Beyond Prompt Routing: Model Selection, Conversation State, and KV Cache

Oct 2, 202611 min read

routing

Per-Call Model Selection: Measuring Cost and Quality Across a Multi-Agent Run

Sep 25, 202615 min read

release

vLLM Semantic Router v0.4 Hermes: Many Models, One Improving System

Sep 24, 202623 min read

release

Introducing Decision 1.0: Open Decision Foundation Models

Sep 22, 202610 min read

release

Introducing Vela 1.0

Sep 18, 202610 min read

community

Find Your Focus: How to Join and Work Together

Aug 24, 202615 min read

hallucination

LettuceDetect v2 in Semantic Router: Generative Hallucination Detection as a vLLM Endpoint

Aug 5, 20269 min read