Hacker News new | past | comments | ask | show | jobs | submit
nullstyle | on: Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering
MLX does not run on NPUs AFAIK; just gpu and cpu. You have to use CoreML to officially run code on the neural engine.
mirsadm | parent
Even then there is no transparency on how it decides what runs on the ANE/GPU etc
sroussey | root | parent
Correct. OS level stuff get first priority, so you can’t count on using it.
loading story #47222052