alt Hacker NewsThe sad part of this is that all those powerful NPUs are basically paperweight.
35-50 low power TOPS taking 1/5 of the die area and not being used by anyone...
Replies
bfrog • today at 1:06 PM
These things are a waste of sand.
Could’ve added more gpu or cpu or cache and people would’ve been happier.
➕ show 2 replies
samrus • today at 1:21 PM
We cantnrun local models on them? They must have some sort of api exposed right? Qualcomm has the Snapdragon Neural Processing Engine iirc
➕ show 2 replies
Local speech recognition is something useful that runs well on a (power efficient) NPU.
Dragon Naturally Speaking used to cost real money and wasn't as accurate as an open model like Whisper.