LLM inference in C/C++

Machine Learning API (Origin: C++: SNAP, C/C#: Tizen API, Java: Samsung-Research ML API)

🔀 Neural Network (NN) Streamer, Stream Processing Paradigm for Neural Network Apps/Devices.

TBD: deviceMLOps.service or deviceMLOps.MLAgent.

NNtrainer is Software Framework for Training Neural Network Models on Devices.

NNStreamer Android Studio Support Resource Files

The best ChatGPT that $100 can buy.

This project is for writing Tizen documents for platform and application developers. The documents will be published to the new Tizen portal site.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

LiteRT is the new name for TensorFlow Lite (TFLite). While the name is new, it's still the same trusted, high-performance runtime for on-device AI, now with an expanded vision.

Verisilicon Tensor Interface Module

An Open Source Machine Learning Framework for Everyone

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Remote source nodes for NNStreamer pipelines without GStreamer dependencies

End-to-end solution for enabling on-device AI across mobile and edge devices for PyTorch models

Supporting PyTorch models with the Google AI Edge TFLite runtime.

Inference Llama 2 in one file of pure C

Neural Network Support for Yocto / OpenEmbedded

Example applications of nnstreamer. Note that we have to enable the 'apptest" CI module in the near future.

Port of OpenAI's Whisper model in C/C++

C# Device APIs for Tizen

FlatBuffers: Memory Efficient Serialization Library

Tensorflow Lite external delegate based on TIM-VX