Hacker News new | ask | show | jobs
by Yukonv 67 days ago
It is possible but requires a very specific model design to utilize. As this reverse engineering effort has shown [0] "The ANE is not a GPU. It’s not a CPU. It’s a graph execution engine." To build one requires using a specific pipeline specifically for CoreML [1].

[0] https://maderix.substack.com/p/inside-the-m4-apple-neural-en... [1] https://developer.apple.com/documentation/coreml

2 comments

That's the best "what is ANE, really?" investigation / explanation I've seen. Directly lays out why LLMs aren't an ideal fit, its "convolution engine" architecture, the need for feeding ANE deep operation sequence plans / graphs (and the right data sizes) to get full performance, the fanciful nature of Apple's performance claims (~2x actually achievable, natch), and the (superior!) hard power gating... just _oodles_ of insight.
More info on specific design choices needed to run models here [1]. I mean it is possible given that apple themselves did it in [2], but it's also not as general purpose or flexible as a GPU.

[1] https://news.ycombinator.com/item?id=43881692 [2] https://machinelearning.apple.com/research/neural-engine-tra...