Hitting a billion tokens per minute on one GPU by combining a query planner and an inference engine

2026-09-28

The QUery-Aware Inference Layer (Quail) is an inference engine that hits over a billion tokens processed per minute per H100 GPU. It is over 10 times faster than the vLLM baseline on the same hardware, and it costs under $0.06 per billion tokens on Modal. This post provides a quick overview of how Quail works. It focuses more on considerations for inference engineers.