Empower conversational AI at scale with KServe

17 · Red Hat · March 15, 2024, 7:39 a.m.
Summary
KServe is a standard Model Inference Platform on Kubernetes built for highly scalable use cases. It is a popular open source platform available as a community project, as well as a core component of Red Hat OpenShift AI. It provides a Kubernetes custom resource definition (CRD) for serving machine learning (ML) models on arbitrary frameworks. It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks and model formats like Te...