Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

ROCm Execution Provider for ONNX Runtime on AMD GPUs. Compiles ONNX models through MLIR to LLVM bitcode, JIT-loads them at session creation, and dispatches to hipDNN, MIOpen, hipBLASLt, and custom …

AI Tensor Engine for ROCm

原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

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

Nano vLLM

Open Machine Learning Compiler Framework

An MIT License of YOLOv9, YOLOv7, YOLO-RD

Offline Quantization Tools for Deploy.

Puzzles for learning Triton

Pytorch and ncnn implementation of PPYOLOE、YOLOX、PPYOLO、PPYOLOv2、PicoDet and so on.

OmniXRI TinyML 小學堂 2025 課程, Arm Cortex-M55, Ethos-U55, Himax WiseEye2 (HX6538, WE2), Seeed Xiao Grove Vision AI Module V2

An MIT License of YOLOv9, YOLOv7, YOLO-RD

Machine learning compiler based on MLIR for Sophgo TPU.

ethos-u-vela is the ML model compiler tool and used to compile a TFLite-Micro model into an optimised version for ethos-u NPU on iMX93 platform

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

On-device AI across mobile, embedded and edge for PyTorch

SGLang is a high-performance serving framework for large language models and multimodal models.

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

YOLOX + ROS2 object detection package (C++ only support)

Use your Neovim like using Cursor AI IDE!

Driving Snax with MLIR

An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).

LLM101n: Let's build a Storyteller 中文版

Edge AI Model Development Tools

YOLOv9MIT + ROS 2 Object Detection demo

Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.