Re:OpenAI Major Outage
by albntomat0 on Wednesday January 25, 2023 @11:55PM
(#34527811)
My understanding is that all the memory has to be GPU memory, with proper interconnects. Still not that crazy, all things considered
> 24x 64 GB nodes is 1.5 TB
Looking at your calculations indicates that you mean RAM but it's 1.5 TB GPU VRAM (but this is assuming they use 64 bit precision, which is likely wrong so it's ~750 GB), not RAM.
To put that in perspective, 24x 64 GB nodes is 1.5 TB.