TensorRT tuner posts up to 1.63-times gains across ten workloads
NVIDIA has detailed the implementation and results of TensorRT 11.1’s Global Performance Tuner. More than 200 compiler knobs can form searchable build routes, with trtexec excluding failed or inaccurate engines before ranking performance. Across ten evaluated workloads, the best eligible routes delivered 1.14-to-1.63-times the default performance, with resumable caches and controlled search modes.