Lists (4)
Starred repositories
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Lightweight LLM inference engine inspired by nano-vllm, with radix-tree based prefix cache, tp & pp, cuda graph, openai api, async scheduling, and more.
Offline optimization of your disaggregated Dynamo graph
FlashInfer: Kernel Library for LLM Serving
Fast and memory-efficient exact attention
A high-throughput and memory-efficient inference and serving engine for LLMs
SGLang is a high-performance serving framework for large language models and multimodal models.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
GPU programming related news and material links
⭐ A simple, fast and powerful blog & document theme built by Astro
collection of benchmarks to measure basic GPU capabilities
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.
Markdown can be used for posting Moments and Docs on my Astro-based site.
An React.js component library for beautifully shaded canvas https://uvcanvas.com
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
A text marking & annotation engine for presenting source code on the web.
Low-JavaScript embed components for Astro websites
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
My personal blog built with Astro, React and Tailwindcss.
Awesome LLM compression research papers and tools.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
A curated list of awesome edge computing, including Frameworks, Simulators, Tools, etc.