AWS Neuron
It supports high-performance training on AWS Trainium-based Amazon Elastic Compute Cloud (Amazon EC2) Trn1 instances. For model deployment, it supports high-performance and low-latency inference on AWS Inferentia-based Amazon EC2 Inf1 instances and AWS Inferentia2-based Amazon EC2 Inf2 instances. With Neuron, you can use popular frameworks, such as TensorFlow and PyTorch, and optimally train and deploy machine learning (ML) models on Amazon EC2 Trn1, Inf1, and Inf2 instances with minimal code changes and without tie-in to vendor-specific solutions. AWS Neuron SDK, which supports Inferentia and Trainium accelerators, is natively integrated with PyTorch and TensorFlow. This integration ensures that you can continue using your existing workflows in these popular frameworks and get started with only a few lines of code changes. For distributed model training, the Neuron SDK supports libraries, such as Megatron-LM and PyTorch Fully Sharded Data Parallel (FSDP).
Learn more
Google AI Edge
Google AI Edge offers a comprehensive suite of tools and frameworks designed to facilitate the deployment of artificial intelligence across mobile, web, and embedded applications. By enabling on-device processing, it reduces latency, allows offline functionality, and ensures data remains local and private. It supports cross-platform compatibility, allowing the same model to run seamlessly across embedded systems. It is also multi-framework compatible, working with models from JAX, Keras, PyTorch, and TensorFlow. Key components include low-code APIs for common AI tasks through MediaPipe, enabling quick integration of generative AI, vision, text, and audio functionalities. Visualize the transformation of your model through conversion and quantification. Overlays the results of the comparisons to debug the hotspots. Explore, debug, and compare your models visually. Overlays comparisons and numerical performance data to identify problematic hotspots.
Learn more
ExecuTorch
ExecuTorch is PyTorch’s open source framework for deploying AI/ML models directly to edge devices, enabling text, vision, speech, recommendation, and multimodal inference without requiring the cloud. It exports models from PyTorch without intermediate conversion formats, preserves ATen operators, and uses ahead-of-time compilation to optimize performance for target hardware before deployment. Its modular design lets developers choose compile-time and runtime optimizations while staying inside the familiar PyTorch ecosystem, including torchao for quantization. A portable C++ runtime with a base footprint of about 50 KB can run on smartphones, desktops, embedded systems, microcontrollers, DSPs, and Cortex-M processors. ExecuTorch supports Android, iOS, Linux, Windows, macOS, and WebAssembly, with native APIs for C++, Swift, Kotlin, and Objective-C.
Learn more
TensorFlow
An end-to-end open source machine learning platform. TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications. Build and train ML models easily using intuitive high-level APIs like Keras with eager execution, which makes for immediate model iteration and easy debugging. Easily train and deploy models in the cloud, on-prem, in the browser, or on-device no matter what language you use. A simple and flexible architecture to take new ideas from concept to code, to state-of-the-art models, and to publication faster. Build, deploy, and experiment easily with TensorFlow.
Learn more
