Dragonfly image service, providing fast, secure and easy access to container images.

Linux kernel source tree -- forked to track pNFS block client commits. Now used to track my patches for Lustre kernel client clean up. well, I'm using it to track my own nfs patches again... And no…

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Command-line tools for managing OCI model artifacts, which are bundled based on Model Spec

A github action for AI assisted PR labeler

🌄 The Cloud Native Interactive Landscape filters and sorts hundreds of projects and products, and shows details including GitHub stars, funding, first and last commits, contributor counts and headq…

Cloud Native Artifacial Intelegence Model Format Specification

Dragonfly is an open source P2P-based file distribution and image acceleration system. It is hosted by the Cloud Native Computing Foundation (CNCF) as an Incubating Level Project.

ModelPack community documents, policies and tools.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

Train your AI self, amplify you, bridge the world

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

[ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

GitHub’s official command line tool

Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel and perform like containers, but provide the workl…

Rust crate for implementing FUSE backends

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Dragonfly related community material

verl: Volcano Engine Reinforcement Learning for LLMs

A Datacenter Scale Distributed Inference Serving Framework

Fully open reproduction of DeepSeek-R1

FlashInfer: Kernel Library for LLM Serving

Distributed RL System for LLM Reasoning