After introducing the first industry-standard inference benchmarks in June of 2019, today the MLPerf consortium released 595 inference benchmark results from 14 organizations. These benchmarks measure how quickly a trained neural network can process new data for a wide range of applications (autonomous driving, natural language processing, and many more) on a variety of form factors (IoT devices, smartphones, PCs, servers and a variety of cloud solutions).
1 comment
[ 4.4 ms ] story [ 15.9 ms ] threadLink to the results: https://mlperf.org/inference-results
Link to white paper: https://edge.seas.harvard.edu/files/edge/files/mlperf_infere...
After introducing the first industry-standard inference benchmarks in June of 2019, today the MLPerf consortium released 595 inference benchmark results from 14 organizations. These benchmarks measure how quickly a trained neural network can process new data for a wide range of applications (autonomous driving, natural language processing, and many more) on a variety of form factors (IoT devices, smartphones, PCs, servers and a variety of cloud solutions).