paper-with-me

Papers

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

2024-05-23 · Jiarui Fang, Jinzhe Pan, Jiannan Wang, Aoyu Li, Xibo Sun

This paper presents PipeFusion, an innovative parallel methodology to tackle the high latency issues associated with generating high-resolution images using diffusion transformers (DiTs) models. PipeFusion partitions images into patches and the model layers across multiple GPUs. It employs a patch-level pipeline parallel strategy to orchestrate communication and computation efficiently. By capitalizing on the high similarity between inputs from successive diffusion steps, PipeFusion reuses one-step stale feature maps to provide context for the current pipeline step. This approach notably reduces communication costs compared to existing DiTs inference parallelism, including tensor parallel, sequence parallel and DistriFusion. PipeFusion also exhibits superior memory efficiency, because it can distribute model parameters across multiple devices, making it more suitable for DiTs with large parameter sizes, such as Flux.1. Experimental results demonstrate that PipeFusion achieves state-of-the-art performance on 8xL40 PCIe GPUs for Pixart, Stable-Diffusion 3 and Flux.1 models.Our Source code is available at https://github.com/xdit-project/xDiT.

📄 PDF Abstract BibTeX arXiv:2405.14430

Code (2)

pipefusion/pipefusion 공식 구현 pytorch
xdit-project/xdit 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

2024-11-04 · Jiarui Fang, Jinzhe Pan, Xibo Sun, Aoyu Li 외

Diffusion models are pivotal for generating high-quality images and videos. Inspired by the success of OpenAI's Sora, the backbone of diffusion models is evolving from U-Net to Transformer, known as Diffusion Transformer…

GPU

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

2024-02-29 · CVPR 2024 1 · Muyang Li, Tianle Cai, Jiaxin Cao, Qinsheng Zhang 외

Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting i…

GPU

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

2025-09-16 · Väinö Hatanpää, Eugene Ku, Jason Stock, Murali Emani 외 arxiv

Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble calibration in weather forecasting comp…

Weather Forecasting

STADI: Fine-Grained Step-Patch Diffusion Parallelism for Heterogeneous GPUs

2025-09-05 · Han Liang, Jiahui Zhou, Zicheng Zhou, Xiaoxi Zhang 외 arxiv

The escalating adoption of diffusion models for applications such as image generation demands efficient parallel inference techniques to manage their substantial computational cost. However, existing diffusion parallelis…

Image Generation

Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference

2024-12-04 · XiuYu Zhang, Zening Luo, Michelle E. Lu

Diffusion models have exhibited exciting capabilities in generating images and are also very promising for video creation. However, the inference speed of diffusion models is limited by the slow sampling process, restric…

DenoisingImage Generation