The MLX software ecosystem, known for its array framework designed for machine learning research, has expanded its support to include new languages such as Swift and C, specifically targeting Apple silicon. This expansion aims to facilitate experimentation for ML researchers by leveraging the native performance and efficiency of Apple's unified GPU and CPU architecture. The MLX Swift and MLX C extensions are available under the MIT license, consistent with the rest of the MLX software ecosystem. Developers have already begun to utilize MLX Swift for projects, including a macOS Local LLM Chat SwiftUI App that operates without an internet connection, and the first app built with MLX Swift, which uses CodeLlama 7B to generate text locally and was open sourced just three days ago. The introduction of MLX Swift has been met with enthusiasm from the community, with developers highlighting the ease of writing code, the framework's potential for on-device machine learning applications, and the regular stream of feature releases from the MLX developers.
I've been really impressed by the regular stream of feature releases from the MLX developers. MLX is definitely a framework to watch. https://t.co/HW1GGPUY8Y
First app built with MLX Swift, just open sourced three days ago 🚀. Uses CodeLlama 7B to generate text locally. Video guide: https://t.co/JeSxPhbifi More MLX Swift examples here: https://t.co/lQs6mECoIK https://t.co/faNwv4PI9O https://t.co/isx0bZyLu7
Experimenting with Apple MLX by creating a macOS Local LLM Chat SwiftUI App. Chat with local LLM Model without internet connection utilizing native performance and efficiency of Apple Silicon Unified GPU & CPU architecture! #LLMs #iosdev https://t.co/LXAnv1HHKZ https://t.co/2TNYH0rF3i
My first change to mlx-swift was merged! Excited to use this framework for on-device ML https://t.co/9pqBgvtoHB
Welcome MLX-Swift! 🍎 Bringing MLX closer to iOS/ Mac developers. Allows you to leverage the metal backend efficiently across Apple devices! Comes with a ready-to-use example for inferring with llama 7B quantised checkpoints. 🔥 GG @awnihannun and team! Y'all are setting the… https://t.co/B7lREmeoru
Looking back at all the amazing things people built with MLX in a couple of months I am incredibly excited to see the things that will be built now in a familiar dev environment in Swift! Just 20 lines of code to write a general multi-head attention in MLX Swift 🚀🚀🚀 https://t.co/beqsZoq1gr https://t.co/jGDGCnMNRp
MLX Swift and MLX C are MIT license just like the rest of the MLX software ecosystem. 🚀
As part of our goal to make MLX a great research tool, we're expanding support to new languages like Swift and C, making experimentation on Apple silicon easier for ML researchers. Video generating text with Mistral 7B and MLX Swift 👇 MLX is an array framework for machine… https://t.co/nKJcgqePyr