F5 NGINX Gateway Fabric is a Kubernetes-native traffic management solution built on the NGINX data plane and Gateway API. It extends traditional application and API routing with AI-aware capabilities designed for increasingly dynamic inference workloads. The solution can route requests according to model type, version, request attributes, performance, cost, availability, and runtime signals such as backend health, queue depth, cache, and memory. Gateway API resources replace fragmented annotation-driven configurations with a structured declarative model that separates platform-team infrastructure responsibilities from developer-controlled routing. Features include advanced Layer 7 routing, weighted traffic splitting, policy attachment, TLS and mTLS, authentication integrations, Prometheus

Join for free to read