Update README.md

Author: shaneutt

README.md

@@ -37,7 +37,7 @@ And the following are more specific terms to this project:
 - **Endpoint Selector**: A `Scheduler` combined with `Metrics and Capabilities`
   systems is often referred to together as an [Endpoint Selection Extension]
   (this is also sometimes referred to as an "endpoint picker", or "EPP").
-- **Inference Gateway**: A proxy/load-balancer which has been coupled with a
+- **Inference Gateway**: Using self-hosted model server, A proxy/load-balancer which has been coupled with a
   `Endpoint Selector`. It provides optimized routing and load balancing for
   serving generative Artificial Intelligence (AI) workloads. It simplifies the
   deployment, management, and observability of AI inference workloads.