Chiplet ASIC supercomputers for LLMs like GPT-4

Re:Chiplet ASIC supercomputers for LLMs like GPT-4 by senttoschool on Wednesday July 12, 2023 @05:47AM (#36692291)

SRAM has stopped scaling based on TSMC's upcoming N3E specs and their planned N2 node specs. So if models are tens of GB large, then I don't see how their proposed chips can be done in an economical way.

Also, a GPU is already an ASIC but with a fancy name.

[ Parent | on HN ]

Re:Chiplet ASIC supercomputers for LLMs like GPT-4 by kraken12 on Wednesday July 12, 2023 @03:02PM (#36700032)

Maybe they could do something like AMD's GPU memory stacking, that is good for scaling, and of course they are using many chips not one chip..

[ Parent | on HN ]

Re:Chiplet ASIC supercomputers for LLMs like GPT-4 by punkgenius on Wednesday July 12, 2023 @05:51PM (#36702196)

Nowadays GPUs have sacrificed some performance for better programmability. ASICs always trade programmability for better performance and energy efficiency, it's really about how 'specific' you want it to be. I guess for applications as important and popular as LLM, we probably want a very 'specific' chip

[ Parent | on HN ]