News for hackers. Stuff that matters.
Re:Accelerated PyTorch Training on M1 Mac by my123 on Wednesday May 18, 2022 @02:35PM (#31426133)
The neural engine is only exposed through a CoreML inference API.

You can't even poke the ANE hardware directly from a regular process. The interface for accessing the neural engine is not hardened (you can easily crash the machine from it).

So the matter is essentially moot in practice as you'd need your users to run with SIP off...

Re:Accelerated PyTorch Training on M1 Mac by viraptor on Thursday May 19, 2022 @03:28AM (#31431742)
That doesn't seem to be a huge issue. If someone actually does this for income, would they avoid disabling sip for 2x performance gain for example?
Re:Accelerated PyTorch Training on M1 Mac by munro on Friday May 20, 2022 @03:35AM (#31444408)
Sounds like you've you done a bit of digging around, you're efforts are appreciated. I found and a github of people sharing what they know, here's a guy live streaming hacking it and building a tinygrad https://youtu.be/mwmke957ki4