Open-source production-ready mobile server-less AI apps. Clone, customize, and ship on Android & iOS with MLange.
Production Android AI with ExecuTorch 1.0 - Deploy PyTorch models to mobile with NPU acceleration and 50KB footprint
Real-time SAM2 segmentation on edge devices - 40x faster C++ inference with ONNX Runtime for iOS/Android deployment
Eklavya: A local-AI "Learning OS" designed to eliminate academic burnout. Powered by AMD Ryzen AI to deliver hyper-personalized, privacy-first cinematic education. +3
A vibe-coded Neural Processing Unit design bundled with a Python testing suite. The design needs extensive testing.
An optimized Softmax approximation framework for NPU-accelerated LLM inference. It features a non-uniform segmentation strategy and variable-degree polynomial approximation optimized via Particle Swarm Optimization (PSO).
Dedicated local OpenAI-Compatible AI Server for Continue.dev with Rich CLI terminal dashboard & DirectML/NPU hardware acceleration
Whisper encoder on the AMD XDNA1 NPU (Ryzen AI, Phoenix) under Linux — open toolchain only: XRT, MLIR-AIE/IRON, peano. Includes an HTTP service speaking whisper.cpp's contract.
To associate your repository with the npu-acceleration topic, visit your repo's landing page and select "manage topics."