A general-purpose lightweight C++ graph library

ALP: Adaptive Lossless Floating-Point Compression

C library for accessing the PostgreSQL parser outside of the server environment

GLake: optimizing GPU memory management and IO transmission.

C++ DataFrame for statistical, Financial, and ML analysis -- in modern C++ using native types and contiguous memory storage

libshmcache is a local cache in the share memory for multi processes. high performance due to read is lockless. libshmcache is 100+ times faster than a remote interface such as redis.

GLM-4-Voice | 端到端中英语音对话模型

A High-Performance JIT-Based C++ Expression/Script Execution Engine with SIMD Vectorization Support

Official inference framework for 1-bit LLMs

Ultra High-performance Lightweight Embedded and Server OLTP RDBMS✨

A native PyTorch Library for large model training

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Vector class library, latest version

Dynamic Memory Management for Serving LLMs without PagedAttention

Low-bit LLM inference on CPU with lookup table

Very fast, high quality, platform-independent hashing algorithm.

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

LLM101n: Let's build a Storyteller

DuckDB is an analytical in-process SQL database management system

A composable and fully extensible C++ execution engine library for data management systems.

Library for specialized dense and sparse matrix operations, and deep learning primitives.

C++ wrappers for SIMD intrinsics and parallelized, optimized mathematical functions (SSE, AVX, AVX512, NEON, SVE))

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

Tile primitives for speedy kernels

Scalable radix top-k selection on GPUs

lightweight, standalone C++ inference engine for Google's Gemma models.

Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

SGLang is a fast serving framework for large language models and vision language models.

cuDF - GPU DataFrame Library

[Start here!] Flow-IPC - Modern C++ toolkit for high-speed inter-process communication (IPC)