Link preview
Benchmark MLPerf Inference: Tiny | MLCommons V1.1 Results
MLPerf Inference: Tiny benchmark suite measures how fast systems can process inputs and produce results using a trained model with v1.1 results. MLCommons · mlcommons.org
DeepGate's model search and compiler produce models that run up to 45× faster and use up to 11× less RAM than reference models on the same microcontroller.
Comments