Stars
Fast and local neural text-to-speech engine
A PWM Instrument driver to control older displays using data from SignalK sources. This is fully configurable and can be calibrated to your display.
🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code
Android Phone Control With Qwen3-VL
🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable
A vector search SQLite extension that runs anywhere!
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Su…
Python CFFI bindings for Raylib
llama.cpp tutorial on Android phone
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
The Kalibr visual-inertial calibration toolbox
Example for OpenVINS running on mobile phone device.
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration
Aim of this repo is provide scripts to simple convert different LLM models to AMD NPU run support.
基于 AMD Ryzen AI (XDNA NPU) 的 YOLOv5s 人脸识别方案。支持全系列锐龙APU（7040/8040/AI 300/MAX），集成环境自检与自动错误报告，实现高性能、低功耗的本地实时推理。
Installation guide for AMD Ryzen AI NPU (XDNA 2) on Framework Laptop 13 with Debian 13. Driver compilation, XRT setup, and 51 TOPS validation.
Sharp Monocular View Synthesis in Less Than a Second
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
MetaDrive: Lightweight driving simulator for everyone
Depth-Anything-V2 tinygrad implementation
A hackable library for running and fine-tuning modern transformer models on commodity and alternative GPUs, powered by tinygrad.