Рет қаралды 102
Saurabh Kulkarni, VP, AI Systems Product Management - Intel
Generative AI and large language models impose several requirements on AI compute systems. One critical demand is the ability to efficiently scale model deployment and service across a wide range of nodes, from a single node to thousands. During this presentation, I will outline our vision for building systems that enable AI customers to seamlessly train and deploy models at scale, leveraging Intel technologies.