DSPy: The framework for programming—not prompting—foundation models

A browser based Pokémon fangame heavily inspired by the roguelite genre.

Self-hosted AI coding assistant

Build smaller, faster, and more secure desktop applications with a web frontend.

Blazingly fast LLM inference.

A pytorch port of Google's RETSim model used in UniSim

NeuSpell: A Neural Spelling Correction Toolkit

RETVec is an efficient, multilingual, and adversarially-robust text vectorizer.

A collection of optimisers for use with candle

An extension library to Candle that provides PyTorch functions not currently available in Candle

Sampling techniques for Candle.

A DKMS package for easy use of Realtek r8125 driver, which supports 2.5 GbE.

The Free Software Media System

OSC App to allow VRChat avatars to interact with eye and facial tracking hardware

Add Support for LSM6DSV16X IMU

Very delicious cakes. Designed by Sorakage

🌱💧 An open source DIY soil moisture sensor

An adapter to make Pimax Foveated Rendering ("LibMagic") work on other headsets.

A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

Tutorial for Porting PyTorch Transformer Models to Candle (Rust)

Large Language Model Text Generation Inference

A blazing fast inference solution for text embeddings models

LLM powered development for VSCode

A guidance language for controlling large language models.

Low rank adaptation (LoRA) for Candle.

Simply connect your haystack pipeline to an vLLM-API server