Заголовок и краткое изложение на выбранном языке ожидают перевода.
用决策模型（如 Jev）逐行调用 API 处理数千行数据效率极低，无法利用查询规划。在单张 H100 上，Qwen3-4B 对 5k 条电影评论做一次 AI 过滤的理论最快速度约为 6.6 秒，目前包括开源 AI-SQL 引擎 Quail 在内的任何系统都远未接近。新博客文章介绍了 Quail 如何基于这一速度上限估算 AI 过滤器的成本。
Полный текст на выбранном языке ожидает перевода. Пока показан оригинал.
Have you tried to use a decision model (like Jev) on thousands of rows? Calling an API once per row is a terrible idea for batch work, because it gets no benefit from query planning and sits *extremely* far from optimal performance.
With Qwen3-4B on one H100, the speed-of-light (SoL) for one AI filter over 5k movie reviews, or the fastest the GPU could possibly run it, is about...6.6 seconds! No system today comes close, including Quail, our open-source AI-SQL engine 😱
New blog post on how we cost AI-powered filters in Quail (based on SoL estimates), check it out! https://fsdatalab.github.io/blog/ai-filter-cost-estimates/
Источник: Shreya Shankar · x.com