According to the document, “Serialized engines are not portable across platforms or TensorRT versions.” what’s the exact meaning of platform? for example, if i build engine in gtx 750, can i run it in gtx 1080?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How can we build a tensorRT model just once and run on different GPUs? | 3 | 429 | May 5, 2020 | |
| Cross Operating System platform compatibility with the same GPU platform | 1 | 456 | April 11, 2022 | |
| Doubts on reusing serialized engines on different platforms or TensorRT versions | 3 | 642 | August 22, 2019 | |
| How to ensure/get portable across GPU platforms? | 2 | 426 | September 1, 2020 | |
| Cross-compilation TensorRT serialized engines | 2 | 949 | October 12, 2021 | |
| Question regarding Tensorrt engine build vs inference environment (TensorRT version, Platform, etc) | 4 | 920 | October 21, 2021 | |
| TensorRT support for multiple GPUs - URGENT | 6 | 2276 | October 28, 2021 | |
| TensorRT model hardware software binding problem | 1 | 358 | November 11, 2022 | |
| Encountered some difficulties on the tensorrt serialization engine | 11 | 1046 | June 7, 2023 | |
| TRT engine across different driver version | 3 | 1468 | December 1, 2020 |