[mrob]

LLM inference is mostly read only, so high-bandwidth flash looks like it could provide huge cost savings over VRAM. It's not yet in commercial products but there are working prototypes already. Previous HN discussion:

https://news.ycombinator.com/item?id=46700384

[whosegotit]

Are you saying that intel’s optane product was just ahead of its time? Is optane the answer to LLM’s ever increasing appetite?