将文生图扩散模型拆成可独立调度的微服务，提升资源利用率和并发能力。
LegoDiffusion: Micro-Serving Text-to-Image Diffusion Workflows
- 将扩散工作流拆分为独立执行节点，实现细粒度资源管理
- 支持单模型弹性伸缩与模型共享，请求吞吐量最高提升3倍
- 适合需要高并发、低延迟的AI图像生成服务场景
文生图生成通过以基础扩散模型为核心的多模型扩散工作流执行。现有服务系统将每个工作流视为封闭的整体，统一分配、部署和扩展所有组成模型，导致内部数据流不透明，无法实现模型复用，并强制粗粒度资源管理。本文提出LegoDiffusion，一种将工作流分解为松耦合模型执行节点的微服务架构，可独立管理与调度。通过显式控制各模型推理，LegoDiffusion实现了集群级优化，包括按模型独立伸缩、模型共享及自适应模型并行。整体性能超越现有扩散工作流服务系统，最高可维持3倍更高的请求速率，并能承受8倍更高的突发流量。
原文摘要 · Abstract (English)
Text-to-image generation executes a diffusion workflow comprising multiple models centered on a base diffusion model. Existing serving systems treat each workflow as an opaque monolith, provisioning, placing, and scaling all constituent models together, which obscures internal dataflow, prevents model sharing, and enforces coarse-grained resource management. In this paper, we make a case for micro-serving diffusion workflows with LegoDiffusion, a system that decomposes a workflow into loosely coupled model-execution nodes that can be independently managed and scheduled. By explicitly managing individual model inference, LegoDiffusion unlocks cluster-scale optimizations, including per-model scaling, model sharing, and adaptive model parallelism. Collectively, LegoDiffusion outperforms existing diffusion workflow serving systems, sustaining up to 3x higher request rates and tolerating up to 8x higher burst traffic.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。