Nvidia triples and Intel doubles generative AI inference performance on new MLPerf benchmark

There are more than 8,500 performance results in the MLCommons' latest benchmark, testing all manner of combinations and permutations of hardware, software and AI inference use cases.

ai benchmark blackwell cases computer components computer hardware computers & electronics generative hardware inference intel large language models llms ml and deep learning mlcommons mlperf mlperf benchmark nvidia open source performance permutations results software tensorrt testing use cases xeon