KServe has officially been accepted as a CNCF incubating project, a significant milestone for this AI inference platform. Designed for scalable deployment on Kubernetes, KServe simplifies the process of running generative and predictive AI workloads. It originated in 2019 from a collaboration among major tech firms like Google, IBM, and NVIDIA, and has evolved significantly since then, transitioning from KFServing to its standalone identity in 2022. Now, it serves a diverse range of industries, with organizations like Bloomberg, SAP, and Red Hat utilizing it for various applications. The platform integrates seamlessly with multiple cloud native technologies, including Kubernetes, Envoy, and Knative, enhancing its functionality. Key features include support for various AI frameworks, autoscaling capabilities, and the ability to manage large-scale AI workloads. KServe's community engagement is robust, with over 4,600 GitHub stars, 2,400 pull requests, and contributions from more than 300 individuals. The maintainers emphasize that KServe is positioned to address the complexities of serving large language models, indicating its relevance in the rapidly evolving AI landscape. Looking ahead, KServe aims to further improve its features, focusing on abstraction and elasticity in inference management. The goal is to allow users to concentrate on their models while KServe manages the underlying orchestration and resource allocation. Being part of the CNCF provides a neutral environment for KServe, ensuring it has the support and governance necessary for continued growth and collaboration within the cloud native ecosystem.