alt Hacker NewsGood point. Maybe there'll be companies that maintain your on-premise GPU cluster just like there are companies that service the coffee machine in your office?
Replies
otabdeveloper4 • yesterday at 8:58 PM
> on-premise GPU cluster
Renting a GPU server from a cloud and hosting your own llama.cpp is the path of least resistance.
This is far more likely than everyone racking their own servers.