Edge and Mobile ML Deployment

LiteRT is a runtime and API for executing machine learning and generative AI models on mobile, desktop, and IoT hardware. It consists of an inference engine and a specialized environment for running quantized large language and diffusion models locally on edge hardware. The system includes an ahead-of-time model compiler that translates models into hardware-specific bytecode to reduce startup latency and memory overhead. It provides a unified interface for Neural Processing Units with automatic fallback routing to CPUs or GPUs when specific subgraph support is unavailable. An edge model conve

GGML is a machine learning tensor library and neural network engine written in C. It functions as a compute-focused runtime designed to execute transformer-based models and perform complex mathematical operations on multi-dimensional arrays directly on local consumer hardware. The library distinguishes itself by enabling local inference for large language models and edge machine learning deployment without reliance on external cloud infrastructure. It achieves this through a tensor-based computation graph that organizes operations for efficient execution and memory management, alongside stati

This project is a cross-platform machine learning inference engine designed to execute pre-trained models across diverse operating systems and hardware environments. It functions as a standardized execution framework that manages the entire lifecycle of model inference, from loading and graph optimization to hardware-accelerated execution and generative sequence management. The runtime distinguishes itself through a highly modular architecture that decouples model logic from hardware-specific kernels. By utilizing an execution provider abstraction, it enables developers to offload computation

MNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

MediaPipe is a cross-platform machine learning framework designed for building and deploying pipelines that process live and streaming media. It provides a system for connecting processing components into custom machine learning chains to analyze real-time audio and video streams. The framework includes a suite of pre-trained models for tasks such as hand, face, and pose tracking, along with tools for retraining and customizing these models with specific datasets. It also features a dedicated benchmarker for measuring the execution speed and accuracy of machine learning models directly within

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

Transformers.js is a JavaScript library and web machine learning framework designed to run pretrained transformer models directly in the browser. It serves as a client-side inference engine and a wrapper for the ONNX Runtime, enabling the execution of multimodal AI tasks on user devices without the need for a backend server. The library distinguishes itself by providing a unified toolkit for processing text, image, and audio data locally. This architecture supports privacy-preserving model inference and reduces latency by performing all computations on the client's hardware. Its capabilities

alpaca.cpp is a high-performance local inference engine implemented in C++ for executing instruction-tuned large language models. It serves as a quantized model runtime designed to load and run model tensors on local hardware with minimal dependencies, removing the requirement for a full Python environment. The project focuses on on-device text generation and the deployment of private AI chatbots. It utilizes model weight quantization to reduce memory requirements and increase inference speed on consumer-grade devices. The system covers hardware-optimized model execution through thread-pool

TVM is a machine learning compiler framework designed to convert deep learning models from various frameworks into optimized machine code. It functions as a cross-platform deployment engine that transforms high-level model definitions into efficient, hardware-specific binaries for diverse computing architectures. The system utilizes a multi-level compilation pipeline that decouples algorithm logic from hardware implementation through tensor-operator abstractions. It employs a graph-level intermediate representation to perform cross-operator optimizations and memory planning before lowering co

This project is a vision language model framework and vision-to-text pipeline designed for deploying and optimizing models that process both images and text. It provides an on-device inference engine and a vision language model framework to run quantized models locally on mobile and desktop hardware accelerators. The framework features a model quantization toolkit to reduce weight precision for lower memory footprints and increased execution speed on specialized silicon. It also includes an efficient vision encoder utilizing a hybrid encoding system to compress image tokens, which reduces pro

TensorFlow is a comprehensive machine learning framework designed for the construction, training, and deployment of complex mathematical models. It utilizes a graph-based execution model that represents operations as directed acyclic graphs, enabling automatic differentiation and efficient parallel processing. The system provides high-level interfaces for defining neural network architectures, alongside a robust engine for managing multidimensional array structures and tensor mathematics. The framework distinguishes itself through a scalable distributed runtime that orchestrates workloads acr

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

Ultralytics is a comprehensive computer vision framework designed for training, validating, and deploying deep learning models across a wide range of visual recognition tasks. It provides a unified interface for core operations including object detection, instance segmentation, pose estimation, and image classification. By utilizing a modular architecture, the platform allows users to swap model components to balance inference speed and accuracy requirements for diverse applications. The framework distinguishes itself through its support for real-time processing and flexible deployment. It in

Apache MXNet is a deep learning framework and distributed machine learning library designed for training and deploying neural networks across distributed systems, mobile devices, and hardware accelerators. It functions as a cross-platform runtime and a dynamic dataflow scheduler that optimizes neural network execution. The framework provides a multi-language API, enabling the development of machine learning models using Python, R, Julia, Scala, Go, and JavaScript. It supports high-performance model training and the scaling of workloads across multiple GPUs and machines. The system covers cap