Apple Quietly Releases MLX, an Open Source Array Framework for Machine Learning on Apple Silicon
“Quietly” is a much-abused adverb in headlines, but I think apt for this. Apple’s machine learning research team has simply released this new framework on GitHub, with no fanfare:
The MLX examples repo has a variety of examples,
including:
Transformer language model training.
Large-scale text generation with LLaMA and finetuning
with LoRA.
Generating images with Stable Diffusion.
Speech recognition with OpenAI’s Whisper.
Seems quite useful already today, and expands the groundwork for on-device AI features in the future.
★
“Quietly” is a much-abused adverb in headlines, but I think apt for this. Apple’s machine learning research team has simply released this new framework on GitHub, with no fanfare:
The MLX examples repo has a variety of examples,
including:
Transformer language model training.
Large-scale text generation with LLaMA and finetuning
with LoRA.
Generating images with Stable Diffusion.
Speech recognition with OpenAI’s Whisper.
Seems quite useful already today, and expands the groundwork for on-device AI features in the future.