Caffe: a fast open framework for deep learning.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

CUDA Templates for Linear Algebra Subroutines

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its…

Tengine is a lite, high performance, modular inference engine for embedded device

🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉

HIP: C++ Heterogeneous-Compute Interface for Portability

oneAPI Deep Neural Network Library (oneDNN)

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end…

ONNX-TensorRT: TensorRT backend for ONNX

Verilator open-source SystemVerilog simulator and lint system

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

A primitive library for neural network

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器

Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.

Compiler Infrastructure for Neural Networks

Poplar libraries

Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv

Implementation of Ternary Weight Networks In Caffe