Protocol Buffers - Google's data interchange format

A library for efficient similarity search and clustering of dense vectors.

Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.

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

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

搞定C++:punch:。C++ Primer 中文版第5版学习仓库，包括笔记和课后练习答案。

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Simplify your onnx model

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

My Solutions to Leetcode problems. All solutions support C++ language, some support Java and Python. Multiple solutions will be given by most problems. Enjoy:) 我的Leetcode解答。所有的问题都支持C++语言，一部分问题支持Jav…

⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tas…

BlazingSQL is a lightweight, GPU accelerated, SQL engine for Python. Built on RAPIDS cuDF.

DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.

HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

Universal model exchange and serialization format for decision tree forests

embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等