Popular GitHub Repositories for On Device Ai

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

[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

Android On_device 1:1 Face Recognition 、 Liveness detection and 1:N & M:N Face Search SDK ? 离线版设备端Android1:1人脸识别 动作活体、静默活体、近红外双目活体检测 以及1:N M:N 人脸搜索算法SDK 封装。全程可开飞行模式不用联网

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

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

Android Input Method Editor (IME) based on Whisper

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

电子鹦鹉 / Toy Language Model

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

Recipes for on-device voice AI and local LLM

Simplified AI runtime integration for mobile app development

Custom implementation of Apple Intelligence features

Object detection inference with Roboflow Train models on NVIDIA Jetson devices.

[NeurIPS'24] DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators

Rediscover the web by browsing the web and get recommendations of new webpages to explore - powered by Gemini Nano

This project implements a complete offline RAG-Fusion application for text generation and retrieval, leveraging efficient local resources.

Android app demonstrating a minimalistic semantic search using Lucene KNN with BERT vocabularies and MiniLM-L6-V2 embeddings.