I found some places have below note:
Note: Serialized engines are not portable across platforms or TensorRT versions.
And I found the explanation is:
TensorRT includes import methods to help you express your trained deep learning model for TensorRT to optimize and run. It is an optimization tool that applies graph optimization and layer fusion and finds the fastest implementation of that model leveraging a diverse collection of highly optimized kernels, and a runtime that you can use to execute this network in an inference context.
My questions are:
- Could I serialize and reuse the engines on different machines (include same platforms and different platforms)? Will they work?
- If they can work, how much loss/extra time cost they would have?
Any comments will be appreciated.