with
Min Chen
(vivo)
,
Jeffrey Morgan
(Ollama)
,
Wenlei (Frank) He
(Google Cloud)
,
Sagar Randive
(Google Cloud)
Dive into the world of serverless GPUs with Cloud Run. This talk explores how Cloud Run delivers on-demand GPUs with unprecedented flexibility and cost efficiency. Learn how you can achieve optimal performance and resource utilization with rapid autoscaling and scaling to zero. And discover how Cloud Run GPUs can help you build AI inference apps with open models, high-performance computing, graphics rendering, and much more.