I built a fleet-scale inference control plane using Crossplane
The article describes how the author built "ModelPlane," a fleet-scale inference control plane using Crossplane. It explains how Crossplane's declarative Kubernetes-native approach was used to manage and orchestrate AI/ML model deployments across large-scale infrastructure, enabling efficient control over inference workloads.
Background
The author built "ModelPlane," an inference control plane using Crossplane (an open-source tool that extends Kubernetes to manage infrastructure as code). This lets teams deploy, scale, and govern AI models (like LLMs) across multiple cloud providers or GPU clusters from a single Kubernetes-based interface. It addresses a growing ops challenge: as companies serve many AI models in production, manually managing routing, scaling, and failover across diverse infrastructure becomes unmanageable. Crossplane treats each model deployment as a "resource" that Kubernetes can reconcile, enabling GitOps-style workflows for AI inference—similar to how DevOps teams manage microservices but applied to ML model serving.