Empowering everyone to host fast and efficient Minecraft servers.

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

A super simple serial terminal

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

HA integration for the Dukaone S6W ventilation heat exchanger

A simple and flexible code for Reservoir Computing architectures like Echo State Networks

Russian Keyboard Registry Script

SponsorBlock integration for podcasts

GPU Approximate Bayesian Computation written in cuda/python3 via pycuda

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Teaching materials for BayesCog at Faculty of Psychology, University of Vienna

A TizenBrew module to remove ads and add support for SponsorBlock for your Tizen TV.

Official inference library for Mistral models

Inference Llama 2 in one file of pure C

Inference Llama 2 in one file of pure C

Open Source Theremin Instrument

Podverse mobile app written in React Native for iOS, Android, and F-Droid

This is a small script to launch the webcam settings dialog from Windows directly.

The MoCap Toolbox is a Matlab® toolbox that contains functions for the analysis and visualization of motion capture data.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RI…

The Hyperscanning Python Pipeline

a python module with GPU

GPU-accelerated Dynamic Time Warp (DTW) Barycenter Averaging

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

GPU-Suite

Framework agnostic python runtime for RWKV models

Running large language models on a single GPU for throughput-oriented scenarios.