alt Hacker NewsOkay, I'll bite. What if your workload genuinely doesn't fit on one machine? Like load balancing or clustering 20+ nodes for LLM inference?
Okay, I'll bite. What if your workload genuinely doesn't fit on one machine? Like load balancing or clustering 20+ nodes for LLM inference?
Your rebuttal to the parent claiming that almost nobody needs k8s is to bring up a workload almost nobody runs? It seems to me like your argument reinforces the parent's, not undermines it.