Kserve

What it does

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

In their own words: KServe - A Kubernetes-native platform for serving machine learning models with standardized protocols for both predictive and generative AI. Scale to zero, GPU acceleration, and multi-framework support.

It's a education tool from Kserve. A free tier lets you try it before paying — useful when you're keeping costs low. Visit the website for the latest features and pricing.