MLCommons announces results from its MLPerf 4.0 inference benchmarks, which added Llama 2 70B and Stable Diffusion XL; systems with Nvidia GPUs came out on top (Samuel K. Moore/IEEE Spectrum)

1 month ago 3

Samuel K. Moore / IEEE Spectrum:
MLCommons announces results from its MLPerf 4.0 inference benchmarks, which added Llama 2 70B and Stable Diffusion XL; systems with Nvidia GPUs came out on top  —  Times change, and so must benchmarks.  Now that we're firmly in the age of massive generative AI, it's time to add two such behemoths …