Can I run an LLM on the device itself
Generated on 8/11/2024
1 search
Yes, you can run a large language model (LLM) on the device itself using Apple's platforms. Apple provides tools and frameworks such as Core ML to facilitate the deployment and execution of machine learning models on their devices. You can start with a model developed in PyTorch, convert it to the Core ML format using Core ML tools, and then integrate it into your app. Core ML optimizes the model for hardware-accelerated execution across the CPU, GPU, and neural engine, making it possible to run models like Whisper, Stable Diffusion, and Mistral on Apple devices.
For more details on running models on device, you can refer to the session Explore machine learning on Apple platforms (07:16).
Explore machine learning on Apple platforms
Get started with an overview of machine learning frameworks on Apple platforms. Whether you’re implementing your first ML model, or an ML expert, we’ll offer guidance to help you select the right framework for your app’s needs.
Platforms State of the Union
Discover the newest advancements on Apple platforms.
Bring your machine learning and AI models to Apple silicon
Learn how to optimize your machine learning and AI models to leverage the power of Apple silicon. Review model conversion workflows to prepare your models for on-device deployment. Understand model compression techniques that are compatible with Apple silicon, and at what stages in your model deployment workflow you can apply them. We’ll also explore the tradeoffs between storage size, latency, power usage and accuracy.
Deploy machine learning and AI models on-device with Core ML
Learn new ways to optimize speed and memory performance when you convert and run machine learning and AI models through Core ML. We’ll cover new options for model representations, performance insights, execution, and model stitching which can be used together to create compelling and private on-device experiences.
Train your machine learning and AI models on Apple GPUs
Learn how to train your models on Apple Silicon with Metal for PyTorch, JAX and TensorFlow. Take advantage of new attention operations and quantization support for improved transformer model performance on your devices.