Implementation of a hierarchical block+associative_scan implementation of mingru

Implement "Were RNNs All We Needed" paper and compare it with original models

This package contains a Keras 3 implementation of the minGRU layer, a minimal and parallelizable version of the gated recurrent unit (GRU)

Implementations of minGru using Jax and Equinox.

xlstm s/m model and mingru - minlstm for parallel concurrency or threads using stacked layers or columns like the cerebral cortex, parallel or distributed concurrent networks, let's try everything except attention :)

Rust port of the official xLSTM repository integrating BitNet (1.58-bit), minGRU, minLSTM, and Transformers in Python and Rust.

minGRU (Feng et al.) in PyTorch, plus a measured ladder of state-tracking recoveries — signed, rotation, and Givens mixers with time decay, all under one parallel scan — with fused Triton GPU kernels as an optional backend