LLMs are driving the frontiers in computer performance today. This talk explores the MLPerf LLM benchmark landscape, the unique challenges of building LLM benchmarks for training and inference, and the challenges for submitters.
David Kanter
David co-founded and is the Head of MLPerf for MLCommons, the world leader in building benchmarks for AI. MLCommons is an open engineering consortium with a mission to make AI better for everyone through benchmarks and data. The foundation for MLCommons began with the MLPerf benchmarks in 2018, which rapidly scaled as a set of industry metrics to measure machine learning performance and promote transparency of machine learning techniques. In collaboration with its 125+ members, global technology providers, academics, and researchers, MLCommons is focused on collaborative engineering work that builds tools for the entire AI industry through benchmarks and metrics, public datasets, and measurements for AI Safety. Our software projects are generally available under the Apache 2.0 license and our datasets generally use CC-BY 4.0.