The ANE is accessible via the CoreML framework, it's a high level interface for ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		my123 on March 30, 2022 \| parent \| context \| favorite \| on: The hunt for the M1’s neural engine The ANE is accessible via the CoreML framework, it's a high level interface for ML inference. It however turns out that a _lot_ of customer apps today don't use those accelerators at all. (and about the attempt at using BNNS functions, that's not offloaded, it runs on the host CPU cores w/ the AMX tightly bound accelerator)

galangalalgol on March 30, 2022 [–]

Would it be possible for someone ro write a onnx runtime utilizing coreml? That would open it up to a lot more applications instantly.

ianai on March 30, 2022 | [–]

ONNX lists CoreML support.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact