🕸️🦀 A WASM vector similarity search written in Rust

Inference Llama 2 in one file of pure C++

LLM inference in C/C++

PhotoMaker [CVPR 2024]

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

lightweight, standalone C++ inference engine for Google's Gemma models.

A local LLM chatbot with RAG for PDF input files

🙌 OpenHands: Code Less, Make More

Train your own small bitnet model

Convolutional Networks with Binary Tree Architectures

Local AI API Platform

Run large language models in Godot.

Self-hosted AI coding assistant

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

C++17 port of Demucs v3 (hybrid) and v4 (hybrid transformer) models with ggml and Eigen3

A fast, local neural text to speech system

Suno AI's Bark model in C/C++ for fast text-to-speech generation

Port of Meta's Encodec in C/C++

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

The collection of pre-trained, state-of-the-art AI models for ailia SDK

🎲 Modern 3D graphics made simple with C++20 cross-platform framework and rendering abstraction API on top of DirectX 12, Vulkan & Metal

so-vits-svc fork with realtime support, improved interface and more features.

Audio Plugin for Audio to MIDI transcription using deep learning.

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

so-vits-svc

Repo of the code from the Medium article - Build a powerful LLM API right on your computer

Streaming of Fine tuned LLM Response using Fast API

Inference Vision Transformer (ViT) in plain C/C++ with ggml

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.