Inference on KubeEdge

Explore edge computing and machine learning inference with KubeEdge in this insightful conference talk. Discover how to leverage KubeEdge's capabilities for deploying and managing machine learning models at the edge, enabling efficient and low-latency inference. Learn about the integration between Seldon, a popular machine learning deployment platform, and KubeEdge, and gain valuable insights into best practices for implementing inference solutions in edge computing environments. Understand the challenges and opportunities of running machine learning workloads on edge devices, and how KubeEdge addresses these issues to provide a seamless experience for developers and data scientists.

Inference on (the) KubeEdge - Adrian Gonzalez-Martin, Seldon