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

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.

AI Edge Quantizer: flexible post training quantization for LiteRT models.

Supporting PyTorch models with the Google AI Edge TFLite runtime.

A high-throughput and memory-efficient inference and serving engine for LLMs

On-device AI across mobile, embedded and edge for PyTorch

Backward compatible ML compute opset inspired by HLO/MHLO

Generative AI extensions for onnxruntime

Open deep learning compiler stack for cpu, gpu and specialized accelerators

리눅스 커널 스터디 2024.11 - (https://www.notion.so/13f0ec8805a080c280cff37af1a8bed0) | Reference: 리눅스 커널 v5.10/15 (iamroot 18차 소스분석용 - 230729 스터디 완주)

This is a collection of our NAS and Vision Transformer work.

A collection of machine learning models for vision optimized for NXP products

Compiler for Neural Network hardware accelerators

KNU_AICOSS_BITSO 공유 레포지토리

Demo of scalable Asterisk on Kubernetes from https://github.com/CyCoreSystems/asterisk-k8s-demo/

Asterisk - mongodb patched mongoose handler

Unofficial Realtime configuration engine and CDR&CEL backend for Asterisk with MongoDB from Minoruta/ast_mongo