Linear Attention Python Packages

taylor-series-linear-attention

Explorations into the recently proposed Taylor Series Linear Attention

leap-transformer

LEAP: Linear Explainable Attention in Parallel for causal language modeling with O(1) path length, and O(1) inference

agent-attention-pytorch

Implementation of Agent Attention in Pytorch

mlx-recurrence

Fused Metal training kernels for linear recurrence on Apple Silicon — SSD (Mamba-2), GLA, RG-LRU, rotational LRU. Flash-linear-attention for MLX: 12-18x less training memory, production-validated.