Re:Chiplet ASIC supercomputers for LLMs like GPT-4
by jacquesm on Wednesday July 12, 2023 @04:34AM
(#36691839)
It's insane because it is theoretical. They haven't shown that it works, think of this paper as a prelude to a funding round or research grant so they have to show some kind of advantage. Which I'm highly skeptical of, usually when papers show this kind of improvement over SOTA it tends to be either a mistake or purposeful nonsense.
[ Parent
| on HN ]
Re:Chiplet ASIC supercomputers for LLMs like GPT-4
by kraken12 on Wednesday July 12, 2023 @03:03PM
(#36700047)
Yeah, a preliminary architectural study to sanity check if an idea could potentially pay off.
Re:Chiplet ASIC supercomputers for LLMs like GPT-4
by mathisfun123 on Thursday July 13, 2023 @12:25AM
(#36705000)
>prelude to a funding round or research grant
Group at my school recently got a grant for 10MM for such a fantasy. All they had was an ISA - no RTL, no functional model, no compiler. Kid in my group (co-advised) is busy scrawling assembly on notebook paper lol. Suffice it to say I don't have high hopes for a tapeout anytime soon.