Starred repositories
Manage multiple AI terminal agents like Claude Code, Aider, Codex, OpenCode, and Amp.
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
Fast, Flexible and Portable Structured Generation
Interactive visualization and analytics on ADS-B data with ClickHouse
A course of learning LLM inference serving on Apple Silicon for systems engineers.
The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.🎉
🛠 A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉
Dataframes powered by a multithreaded, vectorized query engine, written in Rust
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
verl: Volcano Engine Reinforcement Learning for LLMs
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
MCP server to provide Figma layout information to AI coding agents like Cursor
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
DeepEP: an efficient expert-parallel communication library
General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
QwQ is the reasoning model series developed by Qwen team, Alibaba Cloud.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
🌊 Simple, event-driven and stream oriented workflow for TypeScript
Empower the Web community and invite more to build across platforms.
A Datacenter Scale Distributed Inference Serving Framework
A connector for Claude Desktop to read and search an Obsidian vault.