Aug
21
![How TorchServe could scale in a Kubernetes environment using KEDA](/content/images/size/w750/2023/08/ezgif.com-video-to-gif--3--1.gif)
How TorchServe could scale in a Kubernetes environment using KEDA
I almost burned a 7K Euros GPU card (NVIDIA A100 PCIe GPU) to understand how a TorchServe could meet the increasing of ondemand inference requests at scale.
5 min read