Video by CNCF [Cloud Native Computing Foundation] via YouTube

Ajay Vohra of AWS explores a closed-loop approach to placing multiple inference workloads on GPUs using workload profiling, constraint solving, Kubernetes and continuous performance monitoring.
Join us November 9-12 in Salt Lake City.
Explore the Session: https://bit.ly/4yz2EA0
Register: https://bit.ly/3BDI5XL