Featured

From Text to Multimodal Routing: Hardening Vision Signals in vLLM Semantic Router

May 28, 202613 min read

How vLLM Semantic Router hardens multimodal routing by turning visual evidence into trustworthy signals, debugging a Rust/Candle vision-encoder parity issue, and validating image signal correctness for production policy.

Deploying vLLM Semantic Router on AMD Developer Cloud

Mar 25, 202612 min read

v0.3 Themis Roadmap: Stability at Scale

Mar 12, 202610 min read

vLLM Semantic Router v0.2 Athena: ClawOS, Model Refresh, and the System Brain

Mar 10, 202625 min read

Building Mixture-of-Models on AMD GPUs with vLLM-SR

Jan 23, 202610 min read

vLLM Semantic Router v0.1 Iris: The First Major Release

Jan 5, 202610 min read

AMD × vLLM Semantic Router: Building the System Intelligence Together

Dec 16, 202511 min read

Token-Level Truth: Real-Time Hallucination Detection for Production LLMs

Dec 14, 202514 min read

Signal-Decision Driven Architecture: Reshaping Semantic Routing at Scale

Nov 19, 202514 min read

Semantic Tool Selection: Building Smarter AI Agents with Context-Aware Routing

Nov 7, 202511 min read