lazyMonkey69·3 bulan yang lalu·discussI think the paged attention part is a bit oversimplified. Nice read otherwise!
lazyMonkey69·8 bulan yang lalu·discussAlthough not mentioned, I think the exponentially rising costs have something to do with Sora.This along with the fact that it is easier than ever to switch models today. And the fierce competition from Google and Anthropic.Cannot wait for the pump and dump that the OpenAI IPO is going to be.