Skip to content
Open access

Structured sparse attention for accelerating long-context diffusion language models

Nov 2026 · Frontiers in Artificial Intelligence · 0 citations · 36 references

Abstract

Diffusion Large Language Models (DLLMs) have emerged as a compelling parallel decoding paradigm. However, the inherent full bidirectional attention at every denoising step incurs quadratic complexity, imposing severe latency bottlenecks in long-context scenarios. We investigate attention dynamics in DLLMs and propose Structured Sparse Attention (SSA), which uses a fast structure-wise algorithm to select and reuse geometric patterns for inference acceleration. SSA combines cached structured patterns with protection of the active decoding region to balance inference efficiency and output quality. Our investigation reveals a decrease in average adjacent-step attention changes later in denoising, together with vertical and diagonal geometric patterns that motivate sparse-pattern reuse; the trend varies across inputs, layers, and heads. Extensive experiments demonstrate that SSA delivers significant speedups while maintaining competitive quality against previous state-of-the-art methods on the LongBench and RULER benchmarks. At a 128K context length, SSA achieves an end-to-end inference speedup of approximately 2 × . These findings support structured-pattern reuse combined with decoding-region protection as an efficient, training-free approach to accelerating long-context DLLM inference.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.