{"type":"raw_signal","id":"hitting-a-billion-tokens-per-minute-on-one-d93ea7","slug":"hitting-a-billion-tokens-per-minute-on-one-d93ea7","title":"Hitting a billion tokens per minute on one GPU by combining a query planner and an inference engine","description":"Modal and Carnegie Mellon’s Full Stack Data Lab released Quail, an open-source query-aware inference layer for AI-SQL workloads.","retrieval_nugget":"Modal and Carnegie Mellon’s Full Stack Data Lab released Quail, an open-source query-aware inference layer for AI-SQL workloads.","observed_at":"2026-09-27","record_date":"2026-09-27","date_kind":"observed_at","why_it_matters":"Source: https://modal.com/blog/quail-billion-tpm","novelty":"notable","verification_level":"source-linked","signal_type":"research","source_platform":"modal.com","topics":[],"entities":[],"related_patterns":[],"source_url":"https://modal.com/blog/quail-billion-tpm","source_urls":["https://modal.com/blog/quail-billion-tpm"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"signal:hitting-a-billion-tokens-per-minute-on-one-d93ea7","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/signals/hitting-a-billion-tokens-per-minute-on-one-d93ea7/","markdown":"https://newruntime.com/signals/hitting-a-billion-tokens-per-minute-on-one-d93ea7.md","json":"https://newruntime.com/signals/hitting-a-billion-tokens-per-minute-on-one-d93ea7.json"},"next_reads":[{"type":"collection","path":"/signals/","url":"https://newruntime.com/signals/","title":"Raw Signals","reason":"Open every source-linked raw signal.","media_type":"text/html","json_url":"https://newruntime.com/signals.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}
