Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

TinyChatEngine: On-Device LLM Inference Library

On-device Neural Engine

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

A ready-to-use, minimal app that converts any speech into text.

Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.

AubAI brings you on-device gen-AI capabilities, including offline text generation and more, directly within your app.

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

Connect Data Silos with Reliable AI⚡🚀

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Source code for my blog post series "On-device training with Core ML"

This is a web demo for camera-based PPG sensing (rPPG).

Recipes for on-device voice AI and local LLM

Simplified AI runtime integration for mobile app development

Binary Neural Network on IceStick FPGA.

Kotlin bindings for Edgerunner

Custom implementation of Apple Intelligence features