Configure AI Traffic Optimization Features

This section covers the following AI traffic optimization capabilities designed to maximize model throughput, manage resource capacity, and reduce response latency.

In this section

• Intelligent AI Load Balancing
  • Intelligent AI Load Balancing
    • F5BigAnalyzer
    • JSON schema interface
  • F5BigAnalyzer
  • JSON schema interface
  • AI Inference Routing with the F5 Endpoint Picker
    • AI Inference Routing with the F5 Endpoint Picker
    • Configure the Inference Data Path
    • F5 EPP Custom Resource Reference
    • Tune the EPP
    • Verification and Observability for EPP Data Path
    • InferenceObjective and InferenceModelRewrite
• Semantic AI Model Caching