OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

Acceleration package for neural networks on multi-core CPUs

FeatherCNN is a high performance inference engine for convolutional neural networks.

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

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Convolutional Neural Networks

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

Conversion to/from half-precision floating point formats

Legacy mirror of Darwin Kernel. Replaced by https://github.com/apple-oss-distributions/xnu

Caffe2 is a lightweight, modular, and scalable deep learning framework.

Low-precision matrix multiplication

A lightweight parameter server interface

Parameter server framework for distributed machine learning

图解tensorflow 源码

An Open Source Machine Learning Framework for Everyone

LeetCode Problems' Solutions

Preparations for job interview. Contains document, code, blog, question and so forth.