Apple joins AI race with releasing model framework for its silicon chips

As artificial intelligence (AI) takes centre-stage across companies, Apple’s machine learning research team has released frameworks and model libraries designed to run on its silicon chips.

 

The company released MLX, a machine learning framework designed for efficient and flexible machine learning on Apple silicon.

 

“The design of MLX is inspired by frameworks like PyTorch, Jax, and ArrayFire. A noteable difference from these frameworks and MLX is the unified memory model,” according to Apple on GitHub.

 

“Arrays in MLX live in shared memory. Operations on MLX arrays can be performed on any of the supported device types without performing data copies. Currently supported device types are the CPU and GPU,” the Apple ML research team added.

 

Awni Hannun of Apple’s ML team posted on X that just in time for the holidays, “we are releasing some new software from Apple machine learning research”.

 

“MLX is an efficient machine learning framework specifically designed for Apple silicon (i.e. your laptop!),” Hannun said.

 

MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon.

 

“The Python API closely follows NumPy with a few exceptions. MLX also has a fully featured C++ API which closely follows the Python API,” according to the Apple ML team.

 

Last month, Apple CEO Tim Cook revealed that the company is investing quite a bit in AI and will do it responsibly for product enhancements over time.

 

Cook said that the company views AI and machine learning as fundamental technologies and they’re integral to virtually every product that they ship.

 

“When we shipped iOS 17, it had features like Personal Voice and Live Voicemail. AI is at the heart of these features. And then, you can go all the way to the life-saving features on the launch end of the phone like fall detection, crash detection, ECG on the watch. These would not be possible without AI,” he told analysts during the company’s earnings call.

 

Cook said that Apple has work going on related to AI for quite some time.

 

“I’m not going to get into details about what it is, because we really don’t do that. But you can bet that we’re investing, we’re investing quite a bit, we’re going to do it responsibly and you will see product advancements over time,” the Apple CEO said.

 

In August, Cook said the tech giant has been working on generative AI and other models for years.