{"type": "article", "title": ">1B tokens/minute/GPU by combining query planner and inference engine", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/1b-tokens-minute-gpu-by-combining-query-planner-and-inference-engine", "original_source": "https://modal.com/blog/quail-billion-tpm", "published": "2026-09-26T22:41:20+00:00", "accessed": "2026-09-27", "id": "1b-tokens-minute-gpu-by-combining-query-planner-and-inference-engine"}