Replicate 2.2ms inference time on BERT

ghiles August 22, 2019, 5:55pm 1

This is a duplicated topic originally posted in the wrong category. The new topic is here: Replicate 2.2ms inference time on BERT - TensorRT - NVIDIA Developer Forums

Please delete the topic if possible.

Topic		Replies	Views
Replicate 2.2ms inference time on BERT TensorRT	3	853	October 12, 2021
NVIDIA Slashes BERT Training and Inference Times Technical Blog	0	281	August 21, 2022
Inference Benchmarks - TensorRT Version ? TensorRT	1	2044	October 4, 2018
TensorRT 8.0: What’s New TensorRT	2	1149	July 20, 2021
Inference time? Jetson Xavier NX jetson-inference	3	475	October 10, 2021
Inference time using TF-TRT is the same as Native Tensorflow for Object Detection Models TensorRT tensorrt , tf-trt	4	1015	March 31, 2022
NVIDIA Announces TensorRT 8 Slashing BERT-Large Inference Down to 1 Millisecond Technical Blog	0	452	July 20, 2021
TensorRT inference time extremely slow TensorRT	1	459	January 31, 2023
Faster inference in tensorrt model TensorRT tensorrt , jetson-inference	1	399	April 3, 2023
High inference time while running UNet with INT8 precision TensorRT tensorrt	5	998	February 10, 2021