This content originally appeared on DEV Community and was authored by Robert Reilly
Introducing momo-kiji: CUDA for Apple Neural Engine
Cross-posted to Medium and Hashnode
The Problem
Every Apple device has an Apple Neural Engine. Every single one. Billions of them.
Yet most ML developers ignore it completely.
Why? Because there's no good way to target it. CoreML is locked down. You can't bring your own models. You're stuck in Apple's walled garden.
Meanwhile, that ANE sits there doing nothing most of the time—a 10x efficiency boost, completely untapped.
Introducing momo-kiji
Today, we're releasing momo-kiji—an open-source CUDA-like SDK for Apple Neural Engine.
It's simple: compile your model once, target ANE directly, and get 10x better efficiency without rewriting anything.
python
import momo_kiji as mk
# Load any model
model = mk.load("model.onnx")
# Compile for ANE
compiled = model.compile(target="ane")
# Deploy
compiled.save("model_ane.mlmodel")
This content originally appeared on DEV Community and was authored by Robert Reilly
Robert Reilly | Sciencx (2026-03-19T08:42:26+00:00) Intrducing momo-kiji: CUDA for Apple Neural Engine. Retrieved from https://www.scien.cx/2026/03/19/intrducing-momo-kiji-cuda-for-apple-neural-engine/
Please log in to upload a file.
There are no updates yet.
Click the Upload button above to add an update.