Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

关于Transformer模型的最简洁pytorch实现，包含详细注释

A complete computer science study plan to become a software engineer.

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications

Slurm: A Highly Scalable Workload Manager

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

A modern ebook manager and reader with sync and backup capacities for Windows, macOS, Linux, Android, iOS and Web

Readest is a modern, feature-rich ebook reader designed for avid readers offering seamless cross-platform access, powerful tools, and an intuitive interface to elevate your reading experience.

📚 从零开始的大语言模型原理与实践教程

A simple C++11 Thread Pool implementation

workspace是基于C++11的轻量级异步执行框架，支持：通用任务异步并发执行、优先级任务调度、自适应动态线程池、高效静态线程池、异常处理机制等。

Linux kernel stable tree

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

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

YiRage (Yield Revolutionary AGile Engine) - Multi-Backend LLM Inference Optimization. Extends Mirage with comprehensive support for CUDA, MPS, CPU, Triton, NKI, cuDNN, and MKL backends.

AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

nanomsg-next-generation -- light-weight brokerless messaging

ZeroMQ core engine in C++, implements ZMTP/3.1

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

😼 优雅地使用基于 clash/mihomo 的代理环境

Fine-grained GPU sharing primitives

An optimized neural network operator library for chips base on Xuantie CPU.

注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能

FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

The simplest, fastest repository for training/finetuning medium-sized GPTs.