Quail: Open-Source AI-SQL Engine Hits 1B+ Input Tokens/min on One H100
sh_reya · x · 2026-09-25
Shreya Shankar's team open-sourced Quail, an AI-SQL engine built in collaboration with Modal. Its key idea is planning SQL queries and LLM inference jointly: AI-powered data operators form a new class of inference workload, and by co-scheduling queries with inference, Quail reaches 1B+ input tokens/min on a single H100 for one query.
Quoted discussion (Shadaj L) notes systems like this show inference engines need interfaces beyond naive input/output — fine-grained control over schedules and caching will be key.
Related event: UC Berkeley and Modal Open-Source Quail, an AI-SQL Inference Engine(25 posts)→
More from Infra
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- a16z podcast: Mike Volpi on Cisco's 70+ acquisition playbook and the AI buildout — a16z · 2026-11-12
- AMD to pass Intel in server revenue by mid-2027 as share gains 6 points a year — BenBajarin · 2026-11-12
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12