.png){kind=icon}
.png){kind=icon}
Return
ChituDiffusion: A Data-Characteristic-Aware Serving System for Diffusion Models
.png){kind=icon}
PRE
AI
DOI：10.1145/3774934.3786424.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Diffusion models have become the dominant approach for generative tasks in images, videos, and other domains. However, diverse data properties in generation requests, which are critical for efficient serving, remain underexploited. To address this issue, we propose a diffusion model serving system ChituDiffusion. ChituDiffusion leverages the locality of data properties to recompose a diffusion pipeline into subgraphs with shared optimization opportunities, enabling thorough compile-time and runtime co-optimizations. During compilation, ChituDiffusion compiles each subgraph into multiple execution engines optimized for specific data properties. At runtime, heterogeneous requests are elaborately reorganized into fine-grained batching tasks with similar properties and then efficiently executed by matched engines. Evaluation on five diffusion applications shows that ChituDiffusion improves the throughput by up to 2.13x (1.58x on average) on A100 and 2.19x (1.51x on average) on H100 compared with existing frameworks. The code for ChituDiffusion and the production traces have been made open-source at https://github.com/thu- pacman/chitu/tree/ Diffusion.
Keywords:
Deep learining serving system
Diffusion models
Data-characteristic-aware optimization
Compiler