2026
- January 5 - vLLM Semantic Router v0.1 Iris: The First Major Release
- January 23 - Building Mixture-of-Models on AMD GPUs with vLLM-SR
- March 10 - vLLM Semantic Router v0.2 Athena: ClawOS, Model Refresh, and the System Brain
- March 12 - v0.3 Themis Roadmap: Stability at Scale
- March 25 - Deploying vLLM Semantic Router on AMD Developer Cloud
- May 28 - From Text to Multimodal Routing: Hardening Vision Signals in vLLM Semantic Router
- June 2 - Session-Aware Agentic Routing: Continuity-Aware Model Selection for Long-Horizon LLM Agents
- June 5 - vLLM Semantic Router v0.3 Themis: From Signals to Stateful Production Routing
- June 16 - Beyond One Model: Fusion in vLLM Semantic Router
- June 18 - Agentic Routing on AMD ROCm
- June 28 - Giving AgentGateway a Semantic Brain with vLLM Semantic Router
- June 29 - Micro-Agent: Beat Frontier Models with Collaboration inside Model API
- July 9 - Adding Cursor-Style Auto Model Selection to OpenCode with vLLM Semantic Router
- July 21 - Beyond a Single Model: Building Mixture-of-Models Systems with vLLM Semantic Router
- August 5 - Eight MI300X GPUs, Six Open Models, Five Routing Objectives
- August 5 - LettuceDetect v2 in Semantic Router: Generative Hallucination Detection as a vLLM Endpoint
2025
- September 11 - vLLM Semantic Router: Next Phase in LLM inference
- October 20 - Semantic Router Q4 2025 Roadmap: Journey to Iris
- October 27 - From Monolithic to Modular: Scaling Semantic Routing with Extensible LoRA
- November 7 - Semantic Tool Selection: Building Smarter AI Agents with Context-Aware Routing
- November 19 - Signal-Decision Driven Architecture: Reshaping Semantic Routing at Scale
- December 14 - Token-Level Truth: Real-Time Hallucination Detection for Production LLMs
- December 16 - AMD × vLLM Semantic Router: Building the System Intelligence Together