declare-lab/EFLA

Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

🚀 Efficient implementations for emerging model architectures

This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definition as well as triton and cuda kernels for the Sparse Delta Memory layer.

Explorations into the recently proposed Taylor Series Linear Attention

Official Project Page for Deep Delta Learning (https://arxiv.org/abs/2601.00417)

Triton implement of bi-directional (non-causal) linear attention

FLAT: Flash Linear Attention on TPUs

⚡ Official code for “Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus”.

[CVPR 2026 Highlight] Official implementation of Log-linear Sparse Attention (LLSA).