Stars
A tutorial on modern GPU programming for machine learning systems
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.
Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
My learning notes for ML SYS.
A simple VS Code extension to easily visualize git diff files.
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。
SGLang is a high-performance serving framework for large language models and multimodal models.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
A tool for exploring each layer in a docker image
🔬 A fast, interactive web-based viewer for performance profiles.
Fully featured, spec-compliant HTML5 server-sent events library
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
A high-throughput and memory-efficient inference and serving engine for LLMs
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Model Context Protocol(MCP) 编程极速入门
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Open-Source API Development Ecosystem • https://hoppscotch.io • Offline, On-Prem & Cloud • Web, Desktop & CLI • Open-Source Alternative to Postman, Insomnia