VLLM

A collection of 1 Post

Semantic Routing Under the Microscope: Tracing Latency with OpenTelemetry and Coroot

Semantic Routing Under the Microscope: Tracing Latency with OpenTelemetry and Coroot

A deep dive into semantic routing concepts with vLLM Semantic Router on Kubernetes, then adding an observability layer with OpenTelemetry and Coroot to see exactly where every millisecond goes.