LLM inference in C/C++

A framework that helps implementing swizzle GPU kernels

A benchmark framework for decision forest inferences

UNet diffusion model in pure CUDA

Framework for evaluating ANNS algorithms on billion scale datasets.

A library for k-nearest neighbor search

Sample examples of how to call collective operation functions on multi-GPU environments. A simple example of using broadcast, reduce, allGather, reduceScatter and sendRecv operations.

[ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

FlowDroid Static Data Flow Tracker

MPI benchmark to test and measure collective performance

Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite

Compressed Log Processor (CLP) is a free log management tool capable of compressing text logs and searching the compressed logs without decompression.

GPU model checker

The LTSmin model checking toolset

The Git repository for the mCRL2 toolset.

data for the TACO paper

A library for easy and efficient manipulation of tensor networks.

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Hummingbird compiles trained ML models into tensor computation for faster inference.