How Kubernetes Assigns GPUs: Tracing the Device Plugin Path from Pod Spec to CUDA
Share

TL;DR: When you request `nvidia.com/gpu: 1` in a pod spec, the scheduler places the pod on a node that reports a GPU as available. From…

 

 TL;DR: When you request `nvidia.com/gpu: 1` in a pod spec, the scheduler places the pod on a node that reports a GPU as available. From…Continue reading on ITNEXT » Read More Linux on Medium 

#linux

By ali