alt Hacker NewsI hope the LLM wave will leave GPUs behind to go back to pursue more general-purpose computation rather than spending their die area on multiplying 4-bit-number matrices and such things.
I hope the LLM wave will leave GPUs behind to go back to pursue more general-purpose computation rather than spending their die area on multiplying 4-bit-number matrices and such things.
Is that not literally the exect opposite of the direction asics for LLM inference is going?