lucidrains/RLT

Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)

Implementation of a Light Recurrent Unit in Pytorch

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

Official repository of the xLSTM.

Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Mamba SSM architecture

An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages