Fast and low latency asynchronous socket server & client C++ library
Unicorn CPU emulator framework (ARM, AArch64, M68K, Mips, Sparc
Fast and Lightweight Logs and Metrics processor for Linux, BSD, OSX
A lightweight header-only library for using Keras (TensorFlow) models
Distributed parallelization of stencil-based GPU and CPU applications
A high-performance ML model serving framework, offers dynamic batching
Chinese LLaMA & Alpaca large language model + local CPU/GPU training
Polyglot replacement for Ruby WebSocket servers with Action Cable
Library providing end-to-end GPU-accelerated recommender systems
DPDK based 100Gbps network performance and load testing software
A Complete Fast Android Networking Library that also supports HTTP/2
Fast State-of-the-Art Tokenizers optimized for Research and Production
A networking framework that evolves with your application
High quality, fast, modular reference implementation of SSD in PyTorch
Deep Learning API and Server in C++14 support for Caffe, PyTorch
Skytable is a fast, secure and reliable realtime NoSQL database
A set of Docker images for training and serving models in TensorFlow
Socket.IO server implemented on Java
A language for fast, portable data-parallel computation
Linux containers from scratch in C
Ajenti Core and stock plugins
Pre-trained Neural Network models in Axon
RAPIDS Machine Learning Library
Packer templates for building minimal Vagrant baseboxes
The Docker image for Aria2 + AriaNg + File Browser + Rclone