cs.LGNov 8, 2026

MG-Cache: Multi-Granularity Caching for Accelerating Diffusion Transformer Inference

Authors: Zesen Chen, Youxuan Xu, Shigang Li

Organizations: Beijing University of Posts and Telecommunications, China

Abstract

Diffusion Transformer (DiT) models, while having become a powerful backbone for generative synthesis, suffer from high inference cost on generating high-resolution images. Diffusion caching has emerged as a promising acceleration technique to reduce inference cost. However, existing caching strategies fail to accurately identify the varying importance of different computational modules and rarely coordinate cache reusing across the timestep and layer granularities, making it difficult to control error accumulation. To address these limitations, we propose multi-granularity caching (MG-Cache) for DiTs, a novel and fully training-free approach to exploit computational redundancy both on timesteps and Transformer layers. Our core innovation contains a two-stage caching strategy: an offline timestep profiling analysis that identifies redundant timesteps for cache reuse, followed by an adaptive layer-wise caching strategy that combines input stability with importance of each Transformer layer to selectively cache stable Attention and MLP submodules. Extensive experiments on mainstream open-source DiT models validate the effectiveness of our approach, achieving significant acceleration while maintaining high fidelity to the uncached output, with up to a 4.18x acceleration on HunyuanVideo.

Figures & tables

Explore similar work

CardsList
  1. DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

    Apr 4, 2026Haowei Zhu, Ji Liu, Ziqiong Liu +4Diffusion Model Inference AccelerationDiffusion Models

  2. Memory-Efficient Training-Free Acceleration of Diffusion Transformers with BaryCache

    Aug 24, 2026Chengjie Lu, Tianchi Deng, Zhengqi He +3Diffusion Model Inference AccelerationDiffusion-Based Image Generation