Is the Tensorrt model binding with the hardware environment? For example, can the Engine generate on T4 also use on 2080Ti? Is the Tensorrt model binding with the software environment? Only can infer on the same software env where the engine generated ?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Cross Operating System platform compatibility with the same GPU platform | 1 | 440 | April 11, 2022 | |
Cross-compilation TensorRT serialized engines | 2 | 880 | October 12, 2021 | |
Doubts on reusing serialized engines on different platforms or TensorRT versions | 3 | 621 | August 22, 2019 | |
tensorrt-3 portability | 1 | 448 | November 29, 2017 | |
Tensorrt conversion of a model for jetson nano on host device | 4 | 759 | April 27, 2023 | |
Cross compiling (TensorRT serialization, OpenCV, etc) | 4 | 826 | October 18, 2021 | |
How to ensure/get portable across GPU platforms? | 2 | 407 | September 1, 2020 | |
How can we build a tensorRT model just once and run on different GPUs? | 3 | 399 | May 5, 2020 | |
Is it possible to build TensorRT engine for given compute capability (different from device it is running)? | 1 | 419 | February 8, 2021 | |
TRT engine across different driver version | 3 | 1397 | December 1, 2020 |