A real time AI voice assistant for the Jetson Orin Nano. Fully self-contained, runs the Mistral 7B locally, setup a dedicated large language model home assistant using your Jetson Nano.

A collection of scripts to do things with snapshots in bash script form but the main part is the gcloud commands

An Ansible execution environment for AWX project

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Jetson Nano with Ubuntu 20.04 image

An example implementation of AWX on single node K3s using AWX Operator, with easy-to-use simplified configuration with ownership of data and passwords.

COVID-19 themed screensaver for Linux inspired by the classic flying toasters screensaver.

Maps fixes for Synergy Mod

Distribute and run LLMs with a single file.

Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

A simple FastAPI Server to run XTTSv2

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

SOTA Open Source TTS

Instant voice cloning by MIT and MyShell. Audio foundation model.

SD.Next: All-in-one for AI generative image

High-speed Large Language Model Serving for Local Deployment

🔊 Text-Prompted Generative Audio Model

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, D…

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Locally hosted AI code completion plugin for Visual Studio Code

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

Port of OpenAI's Whisper model in C/C++

A high-throughput and memory-efficient inference and serving engine for LLMs

Fast audio player, recorder, converter for Windows, Linux & Android

Letta (formerly MemGPT) is a framework for creating LLM services with memory.

Python bindings for llama.cpp

CLIP inference in plain C/C++ with no extra dependencies