Multi-round diffusion image editing can reduce computation by reusing intermediate activations, but retaining these activations across editing rounds introduces substantial memory and bandwidth overheads. Compression can reduce these overheads, but efficient cache construction is challenging: compressing only after editing requires buffering over 100 GB of activations per request. Moreover, the compressed cache must support selective reuse, as future masked edits require only a subset of the cached activations. It also exposes a scheduling challenge, as cached edits are faster than initial generations, causing naive policies to severely delay either initial generations or editing requests. In this paper, we aim to address both challenges through compression-informed serving. We develop TileCache, a serving system for multi-round diffusion editing. It compresses reusable activations and incorporates a scheduler that balances both edits and initial generation requests. Compared with the state-of-the-art image editing baseline, TileCache sustains over 2x the request arrival rate at 90% SLO attainment. It completes edits 2.4-4.5x and initial generations 1.3-2.2x faster than the baseline, while preserving image quality.


翻译:暂无翻译

0
下载
关闭预览

相关内容

VIP会员
最新内容
《美空军2026条令文件:对海压制作战》
专知会员服务
25+阅读 · 11月9日
人工智能与战争的未来
专知会员服务
10+阅读 · 11月8日
《Agent Mosaic:识别智能体LLM系统中的机密泄露》
专知会员服务
12+阅读 · 11月8日
人工智能在军事教育中的应用:若干视角与经验
专知会员服务
13+阅读 · 11月6日
“星链”减速与不断适应的乌克兰
专知会员服务
10+阅读 · 11月6日
美国中期选举之后:帕兰提尔面临不确定性?
专知会员服务
7+阅读 · 11月6日
Top
微信扫码咨询专知VIP会员