Intelligent AI Load Balancing

This EA feature provides dynamic, intelligent traffic distribution for Large Language Model (LLM) inference workloads on BIG-IP Next for Kubernetes, following the NVIDIA LLM Router blueprint architecture.

---

This document explains how to understand, configure, and install the AI LB feature on an existing BIG-IP Next for Kubernetes deployment.

• Core Components

• Prerequisites

• CR Parameters

• Built-in Script

• Custom Script

• JSON Schema Interface