Sign Up
OverviewAPI
Nvidia and Intel make remarkable strides in AI inference performance on the MLPerf 4.0 benchmark. Nvidia triples performance using H100 Hopper GPU for text summarization, while Intel enhances speeds with Habana AI accelerator and 5th Gen Intel Xeon processor. New models like Llama 2 and Stable Diffusion are now part of the benchmark.

Ask a question