FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

NeurIPSSpotlight2025

Authors
Akide Liu, Zeyu Zhang, Zhexin Li, Xuehai Bai, Yuanjie Xing, Yizeng Han, Jiasheng Tang, Jichao Wu, Mingyang Yang, Weihua Chen, Jiahao He, Yuanyu He, Fan Wang, Gholamreza Haffari, Bohan Zhuang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Diffusion generative models have become the standard for producing high-quality, coherent video content, yet their slow inference speeds and high computational demands hinder practical deployment…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

generative model attention diffusion sparsity video

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive