Tag
Modal and Carnegie Mellon University's Full Stack Data Lab developed Quail, an inference engine that integrates query planning with inference to achieve over a billion tokens processed per minute on a single H100 GPU, outperforming vLLM by 10x in specific scenarios.
Quail is an open source AI-SQL engine that integrates query planning with LLM inference to achieve over 1 billion input tokens per minute on an H100 GPU.
Introduces Spider 2.0-AIFunc, a benchmark of 465 instances across 125 real-world databases for evaluating AI-native SQL queries that use cloud platform AI functions. Evaluates ten state-of-the-art models, finding proprietary models reach 67-70% accuracy while open-source models lag behind.