This package contains a Keras 3 implementation of the minGRU layer, a minimal and parallelizable version of the gated recurrent unit (GRU)
-
Updated
May 23, 2025 - Python
#
mingru
Here are 7 public repositories matching this topic...
Implement "Were RNNs All We Needed" paper and compare it with original models
python ai deep-learning neural-network python3 pytorch lstm gru neural-networks rnn pytorch-implementation minlstm mingru
-
Updated
Sep 26, 2025 - Jupyter Notebook
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 :)
-
Updated
Feb 14, 2026 - 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
cuda pytorch recurrent-neural-networks gru triton rnn gpu-kernels givens-rotations parallel-scan expressivity sequence-modeling paper-implementation time-decay state-tracking linear-rnn mingru orthogonal-rnn
-
Updated
Jul 25, 2026 - Python
Improve this page
Add a description, image, and links to the mingru topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the mingru topic, visit your repo's landing page and select "manage topics."