Featured

How vLLM Semantic Router Trains Embedding Models and Publishes Them to Hugging Face

Jul 25, 20266 min read

End-to-end walkthrough of fine-tuning cache LoRA and domain-adapted embeddings, evaluating them, uploading to llm-semantic-router on Hugging Face, and using them for routing and semantic cache.

Beyond a Single Model: Building Mixture-of-Models Systems with vLLM Semantic Router

Jul 21, 202621 min read

Adding Cursor-Style Auto Model Selection to OpenCode with vLLM Semantic Router

Jul 9, 202611 min read

Micro-Agent: Beat Frontier Models with Collaboration inside Model API

Jun 29, 202612 min read

Giving AgentGateway a Semantic Brain with vLLM Semantic Router

Jun 28, 202610 min read

Agentic Routing on AMD ROCm

Jun 18, 202614 min read

Beyond One Model: Fusion in vLLM Semantic Router

Jun 16, 202613 min read

vLLM Semantic Router v0.3 Themis: From Signals to Stateful Production Routing

Jun 5, 202623 min read

Session-Aware Agentic Routing: Continuity-Aware Model Selection for Long-Horizon LLM Agents

Jun 2, 202620 min read

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

May 28, 202613 min read