Re:Nvidia pursues $30B custom chip opportunity with new unit
by wmf on Sunday February 11, 2024 @02:40PM
(#39337905)
These technologies have already been explored and they failed every time. It's throwing good money after bad.
Also, speculative basic research isn't comparable to adding more RAM to a graphics card. You can't substitute one for the other.
Just ten years back, squeezing ML models onto microcontrollers sounded completely insane, given their tight memory and power constraints. We've seen NN compilers developed, game-changing techniques like quantization, pruning, and graph-level optimizations pruning. This allowed deployment of ML models in microcontrollers with a newly developed framework like TFLite Micro.