Can I read CacheQuant: Comprehensively Accelerated Diffusion Models on EtoBox?

CacheQuant: Comprehensively Accelerated Diffusion Models by Liu, Xuewen; Li, Zhikai; Gu, Qingyi is a scholarly article available to read on EtoBox.

What is CacheQuant: Comprehensively Accelerated Diffusion Models about?

Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at both levels can compound the acceleration effects. Unfortunately, we find that the optimizations at these two levels are not entirely orthogonal. Performing separate optimizations and then simply integrating them results in unsatisfactory performance. To tackle this issue, we propose CacheQuant, a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques. Specifically, we employ a dynamic programming approach to determine the optimal cache schedule, in which the properties of caching and quantization are caref

Author

Liu, Xuewen; Li, Zhikai; Gu, Qingyi

Published

2025

Language

EN