bowin

Allocator

Ultra fast C++11 allocator for STL containers.

mmap_allocator

A STL allocator that mmaps files

mem0

The memory layer for Personalized AI

pose-monitor

“让爷康康”是一款手机 AI 应用程序，可以监测不良坐姿并进行语音提示

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

vanna

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

EmbedAnything

A minimalist yet highly performant, lightweight, lightening fast, multisource, multimodal and local embedding solution, built in rust.

dictionary

High-performance dictionary coding

ngram

The n-gram Language Model

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

gpu.cpp

A lightweight library for portable low-level GPU computation using WebGPU.

openvdb

OpenVDB - Sparse volume data structure and tools

disruptor-rs

Low latency inter-thread communication library in Rust inspired by the LMAX Disruptor.

OI-wiki

:star2: Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

bpe.c

Simple Byte pair Encoding mechanism used for tokenization process . written purely in C

concurrentqueue

A fast multi-producer, multi-consumer lock-free concurrent queue for C++11

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

passport-clerk-quickstart

LLM101n

LLM101n: Let's build a Storyteller

hands-on-time-series-analylsis-python

Source Code for 'Hands-on Time Series Analysis with Python' by B V Vishwas and Ashish Patel

Reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学

numpy-ml

Machine learning, in numpy

Template-Metaprogramming-with-CPP

Template Metaprogramming with C++, published by Packt

xsimd

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

llama_index

LlamaIndex is a data framework for your LLM applications

ESP32Servo

Arduino-compatible servo library for the ESP32

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

InvokeAI

InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

instructor

structured outputs for llms