Catalog

As the gen AI revolution unfolds, organizations must navigate the operational challenges of scaling GPU workloads in the cloud. When it comes to AI inference or how AI analyzes and draws conclusions from new data, Kubernetes offers a compelling yet challenging solution. Optimizing AI inference workloads requires deep understanding of Kubernetes and AI models. Setting appropriate resource requests and limits for containers, especially for AI workloads, is tricky. Incorrect settings lead to cost overruns, and/or inefficient resource utilization. In this session, learn how to leverage the power of Kubernetes with AWS and NetApp to overcome the challenges of optimizing GPU infrastructure. This presentation is brought to you by NetApp, an AWS Partner.