FlashInfer: Kernel Library for LLM Serving

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Intelligent automation and multi-agent orchestration for Claude Code

Fast C++ logging library.

A C++ parser combinator library.

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

A high-performance, extensible Python AOT compiler.

FlashMLA: Efficient Multi-head Latent Attention Kernels

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

PyTorch Tutorial for Deep Learning Researchers

Design Patterns In Modern C++ 中文版翻译

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Low-latency machine code generation

Linq for list comprehension in C++

Havenask is a large-scale distributed information search system widely used within Alibaba Group

Freestanding fast input/output for C++20

广告检索引擎(针对在线广告设计，支持简单倒排检索、范围检索、LBS检索，持续完善中)

High-Performance C++ Fundamental Library

Dapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration.

Proxy: Next Generation Polymorphism in C++

精选机器学习，NLP，图像识别， 深度学习等人工智能领域学习资料，搜索，推荐，广告系统架构及算法技术资料整理。算法大牛笔记汇总

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

c/c++ log benchmark

Extremely fast Query Engine for DataFrames, written in Rust

A curated list of awesome parallel computing resources

C++ multi-dimensional labeled arrays and dataframe based on xtensor

C++ DataFrame for statistical, financial, and ML analysis in modern C++

oneAPI Threading Building Blocks (oneTBB)