Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-$K$ sparse attention approaches reduce the computation of DiTs by compressing tokens into block-wise representation and selecting a small set of relevant key blocks, but still suffer from (i) quadratic selection cost on compressed tokens and (ii) increasing $K$ required to maintain model quality as sequences grow. We identify that their inefficiency is due to the single-level design, as a single coarse level is insufficient to represent the global structure.In this paper, we introduce Log-linear Sparse Attention (LLSA), a trainable sparse attention mechanism for extremely long token sequences that reduces both selection and attention costs from quadratic to log-linear complexity by utilizing a hierarchical structure. LLSA performs hierarchical Top-$K$ selection, progressively adopting sparse Top-$K$ selection with the indices found at the previous level,and introduces a Hierarchical KV Enrichment mechanism that preserves global context while using fewer tokens of different granularity during attention computation. To support efficient training, we develop a high-performance GPU implementation that uses only sparse indices for both the forward and backward passes, eliminating the need for dense attention masks.We evaluate LLSA on high-resolution pixel-space image generation without using patchification and VAE encoding. LLSA accelerates attention inference by $ 28.27 \times$ and DiT training by $ 6.09 \times$ on $256 \times 256$ pixel token sequences, while maintaining generation quality. The results demonstrate that LLSA offers a promising direction for training long-sequence DiTs efficiently.