The readme has been updated to show that an "Inference Gateway" means a "proxy/load-balancer which has been coupled with an Endpoint Picker. It provides optimized routing and load balancing for serving Kubernetes self-hosted generative Artificial Intelligence (AI) workloads. It simplifies the deployment, management, and observability of AI inference workloads."

It would be very helpful to update our website, particularly our main page, to adopt similar terminology, as the "Inference Gateway" idea is both easier to say and remember.

/kind documentation