AIOS: AI Agent Operating System

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)

LvLLM is a special NUMA extension of vllm that makes full use of CPU and memory resources, reduces GPU memory requirements, and features an efficient GPU parallel and NUMA parallel architecture, su…

revng: the core repository of the rev.ng project

FlagTree is a unified compiler supporting multiple AI chip backends for custom Deep Learning operations, which is forked from triton-lang/triton.

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉

开源开发工具周刊

🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧

3D astronomy and space exploration program.

Inference Llama 2 in one file of pure C

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …

Python tool for converting files and office documents to Markdown.

A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.

Open-source Pricing and Billing Infrastructure 🚀 Subscription management, Invoicing, Pricing, Usage-based billing, Cost limiting, Grandfathering, Experiments, Revenue analytics & Actionable insights

Financial data platform for analysts, quants and AI agents.

Official inference framework for 1-bit LLMs

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

Waydroid uses a container-based approach to boot a full Android system on a regular GNU/Linux system like Ubuntu.

Programmable debugger

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

Rust keyboard firmware library with layers, macros, real-time keymap editing, wireless(BLE) and split support

Handwriting synthesis with Harfbuzz WASM.

Fast, flexible LLM inference

Rust implementation of behavior trees for deterministic AI

A real-time multiplayer card game of "Set".

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.