Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.14741 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911205166153728 |
|---|---|
| author | Wang, Kunyun Li, Bohan Yu, Kai Guo, Minyi Zhao, Jieru |
| author_facet | Wang, Kunyun Li, Bohan Yu, Kai Guo, Minyi Zhao, Jieru |
| contents | Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the inherently sequential nature of the denoising process. While existing parallelization strategies attempt to accelerate inference by distributing computation across multiple devices, they typically incur high communication overhead, hindering deployment on commercial hardware. To address this challenge, we propose \textbf{ParaStep}, a novel parallelization method based on a reuse-then-predict mechanism that parallelizes diffusion inference by exploiting similarity between adjacent denoising steps. Unlike prior approaches that rely on layer-wise or stage-wise communication, ParaStep employs lightweight, step-wise communication, substantially reducing overhead. ParaStep achieves end-to-end speedups of up to \textbf{3.88}$\times$ on SVD, \textbf{2.43}$\times$ on CogVideoX-2b, and \textbf{6.56}$\times$ on AudioLDM2-large, while maintaining generation quality. These results highlight ParaStep as a scalable and communication-efficient solution for accelerating diffusion inference, particularly in bandwidth-constrained environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14741 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism Wang, Kunyun Li, Bohan Yu, Kai Guo, Minyi Zhao, Jieru Machine Learning Artificial Intelligence Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the inherently sequential nature of the denoising process. While existing parallelization strategies attempt to accelerate inference by distributing computation across multiple devices, they typically incur high communication overhead, hindering deployment on commercial hardware. To address this challenge, we propose \textbf{ParaStep}, a novel parallelization method based on a reuse-then-predict mechanism that parallelizes diffusion inference by exploiting similarity between adjacent denoising steps. Unlike prior approaches that rely on layer-wise or stage-wise communication, ParaStep employs lightweight, step-wise communication, substantially reducing overhead. ParaStep achieves end-to-end speedups of up to \textbf{3.88}$\times$ on SVD, \textbf{2.43}$\times$ on CogVideoX-2b, and \textbf{6.56}$\times$ on AudioLDM2-large, while maintaining generation quality. These results highlight ParaStep as a scalable and communication-efficient solution for accelerating diffusion inference, particularly in bandwidth-constrained environments. |
| title | Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.14741 |