Machine learning innovation to benefit everyone.
MLPerf™ Training v1.1 ResultsMachine learning performance trajectory increases up to 30X since first release in 2018 helping to propel AI development
MLPerf™ HPC v1.0 resultsIntroducing a new machine learning metric for supercomputers and a graph neural network benchmark for molecular modeling
MLPerf™ Inference v1.1 ResultsLatest round Includes over 1,800 performance and 350 power results for leading ML inference systems
MLPerf™ Training v1.0 ResultsThe latest benchmark submission round includes nearly 150 ML Training performance results for leading ML models, software, and hardware
MLCommons aims to accelerate machine learning innovation to benefit everyone.
MLCommons aims to accelerate machine learning innovation to benefit everyone. Machine learning has tremendous potential to save lives in areas like healthcare and automotive safety and to improve information access and understanding through technologies like voice interfaces, automatic translation, and natural language processing. However, machine learning is completely unlike conventional software -- developers train an application rather than program it -- and requires a whole new set of techniques analogous to the breakthroughs in precision measurement, raw materials, and manufacturing that drove the industrial revolution.
MLCommons aims to answer the needs of the nascent machine learning industry through open, collaborative engineering in three areas:
Benchmarks provide consistent measurements of accuracy, speed, and efficiency. Consistent measurements enable engineers to design reliable products and services, and enable researchers to compare innovations and choose the best ideas to drive the solutions of tomorrow.
Datasets are the raw materials for all of machine learning. Models are only as good as the data they are trained on. Academics and entrepreneurs in particular depend on public datasets to create new technologies and new companies.
Best Practices empower researchers and engineers to more easily exchange models, reproduce experiments, and build applications that leverages machine learning. Improving best practices accelerates progress in, and grows the market for, machine learning.
People’s Speech is an open speech recognition dataset containing over 87,000 hours -- 10 years -- of labeled speech in multiple languages. It is approximately 100x larger than existing open alternatives. People’s Speech was inspired by the success of the open dataset ImageNet in catalyzing a wave of innovation that propelled the field of computer vision forward. People’s Speech aims to similarly advance the state-of-the-art in speech-to-text, benefiting speakers of diverse languages around the world. More diverse speech support is crucial because smart speakers and voice assistants will reach nearly everyone on the planet by 2025.
MLCube is a set of best practices for creating ML software that can just "plug-and-play" on many different systems. MLCube makes it easier for researchers to share innovative ML models, for a developer to experiment with many different models, and for software companies to create infrastructure for models. It creates opportunities by putting ML in the hands of more people. MLCube isn’t a new framework or service; MLCube is a consistent interface to machine learning models in containers like Docker. Models published with the MLCube interface can be run on local machines, on a variety of major clouds, or in Kubernetes clusters -- all using the same code.