AI Briefing#core-ml
The latest AI and developer news about #core-ml, with the original source and a short summary.
The latest AI and developer news about #core-ml, with the original source and a short summary.
AnySpeechRecognizer, a Swift package that reimplements the Apple Speech API to enable the use of open models, and AnyDecisionModel for decision tasks have been released.
A research paper that reverse-engineers and analyzes the architecture and operating principles of the Neural Engine (ANE), Apple Silicon's AI accelerator.
AnyLanguageModel, a Swift package that lets developers manage local and cloud LLMs on Apple platforms through a single unified API, has been released.
Introduces methods for converting RedNote's 3B-parameter OCR model, dots.ocr, to Core ML and MLX to run on the Apple Neural Engine.
Hugging Face released version 1.0 of the Swift library that supports local LLM integration on Apple Silicon.
Introduces a method for efficiently running the Mistral 7B model on Mac by leveraging Apple's new Core ML features.
Apple and Hugging Face have released Core ML optimization and quantization techniques to run SDXL efficiently on Mac.
Through Apple's Core ML optimizations and 6-bit palettization, Stable Diffusion can run faster and more efficiently on Apple devices.
Hugging Face has released a native app that runs Stable Diffusion quickly on Mac by leveraging Core ML.
Reveals how to run Stable Diffusion on Apple Silicon via Core ML and releases the converted models.