Nice demo, I like how clearly you explain all the steps and concepts. Is there a repo somewhere with the steps to reproduce? I'm interested in running inference in a custom k8s cluster using spinkube.
In local architecture we trade procesing power with security/privacy. In cloud based the opposite. I don't get the advantages of the hybrid architecture to be honest! I get the "how" from the video (great one btw) but I think i'm missing the "why"
@@glitchinLife that’s a fair point. However I (Thorsten) was working with many corporations, which required persistence of data on-premises. If one is facing regulatory compliances like that, it could be handy to offload inferencing, while having compute and persistence on-premises.
Nice demo, I like how clearly you explain all the steps and concepts. Is there a repo somewhere with the steps to reproduce? I'm interested in running inference in a custom k8s cluster using spinkube.
@@cloud-native-corner thanks. 🙏🏻. We‘re in the process of creating and publishing an article that guides you through everything.
In local architecture we trade procesing power with security/privacy. In cloud based the opposite. I don't get the advantages of the hybrid architecture to be honest! I get the "how" from the video (great one btw) but I think i'm missing the "why"
@@glitchinLife that’s a fair point. However I (Thorsten) was working with many corporations, which required persistence of data on-premises. If one is facing regulatory compliances like that, it could be handy to offload inferencing, while having compute and persistence on-premises.
I love this :)
Thank you 🙏🏼