I just stumbled across this repository on GitHub, MLX: An array framework for Apple silicon https://github.com/ml-explore/mlx
MLX is a NumPy-like array framework designed for efficient and flexible machine learning on Apple silicon, brought to you by Apple machine learning research.
The Python API closely follows NumPy with a few exceptions. MLX also has a fully featured C++ API which closely follows the Python API.
To install from PyPI you must meet the following requirements:
- Using an M series chip (Apple silicon)
- Using a native Python >= 3.8
- MacOS >= 13.3
|
1 |
pip install mlx |
It is also possible to build from source, with these requirements
- A C++ compiler with C++17 support (e.g. Clang >= 5.0)
- cmake – version 3.24 or later, and
make - Xcode >= 14.3 (Xcode >= 15.0 for MacOS 14 and above)
There are detailed instructions on use https://ml-explore.github.io/mlx/build/html/index.html
Looks like I’ll be busy over the Christmas break exploring and testing. I’d be interested if anyone has had a look at this.