Modal uses evals and inference-time compute scaling to generate beautiful and scannable QArt codes
Original title:How we used evals and inference-time compute scaling to generate beautiful QR codes that actually work
AI summary
Modal's team reviewed the engineering process behind its QArt codes service, using evals and inference-time compute scaling to raise the QR code scan rate to a 95% SLO while improving aesthetics and keeping p95 end-to-end latency under 20 seconds.
Quick Facts
- Published
- Updated
- Source
- Modal 官方工程博客(RSS)
- Category
- Tutorials & Tips
- AI score
- 62
Modal 团队复盘 QArt codes 从不可扫到 95% 扫描率的工程路径,evals 构建与推理时并行扩展的方法可迁移到其他生成模型应用。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Modal uses evals and inference-time compute scaling to generate beautiful and scannable QArt codes. July 2, 2025. https://new.nat6.net/en/news/cmtyq5ikh001droupfg753sg4/