Video by CNCF [Cloud Native Computing Foundation] via YouTube

Weiqi Sun of NVIDIA explores how workload profiling, constraint solving and continuous monitoring can place multiple models on compatible GPUs and improve accelerator utilization on Kubernetes.
Join us November 9-12 in Salt Lake City.
Explore the Session: https://bit.ly/4yz2EA0
Register: https://bit.ly/3BDI5XL