Quail: open-source AI-SQL engine hits 1B+ tokens/min on a single H100

sh_reya · x · 2026-09-25

Quail, a new open-source AI-SQL engine built with Modal, plans queries and LLM inference together, reaching 1B+ input tokens/min on a single H100 for one query. It targets the emerging workload of AI-powered data operators.

Related event: UC Berkeley and Modal Open-Source Quail, an AI-SQL Inference Engine(25 posts)→

Original post →

More from Infra

Infra channel →