Mlcommons Releases New Mlperf Results That Highlight Growing Importance Of Generative Ai And Storage

MLCommons, the leading open AI engineering consortium, announced new results from two MLPerf™ benchmark suites: MLPerf Inference v3.1 and MLPerf Storage v0.5. MLPerf Inference v3.1 includes record participation, with over 13,500 performance results and up to 40% performance gains, from 26 different submitters. MLPerf Inference v3.1 measures how fast systems can run models in a variety of deployment scenarios, and introduces two new benchmarks to the suite: a large-scale language modeling (LLM) benchmark and a recommendation benchmark. MLPerf Storage v0.5 measures the performance of storage systems in the context of ML training workloads.