The specification of the Model Context Protocol

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Desktop signer and key management app.

DeepSeek Coder: Let the Code Write Itself

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Reverse engineered Linux driver for the Apple Neural Engine (ANE).

Minimalist ML framework for Rust

Fast and memory-efficient exact attention

A fast inference library for running LLMs locally on modern consumer-class GPUs

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

zero-shot realtime TTS system, fully offline, free and open source

Official inference repo for FLUX.1 models

Quick Mflux on ComfyUI

Examples in the MLX framework

MLX: An array framework for Apple silicon

A MLX port of FLUX based on the Huggingface Diffusers implementation.

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

Fast word vectors with little memory usage in Python

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

Bloom-filter based minimal perfect hash function library

Fast and scalable minimal perfect hashing for massive key sets

The enum Either with variants Left and Right is a general purpose sum type with two cases.

Rich text layout library

A crate to use `glyphon` within `egui`

A new markup-based typesetting system that is powerful and easy to learn.

The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".