I am trying to use TensorRT to accelerate computation in deployment phrase. I use an HP Omen notebook with a 1070 Max-Q GPU, but it turns out to be “platform does not have FP16 support”. I searched on google and the results suggest it does support FP 16. Why does this happen to how to solve it?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
FP16 Issue on hardware | 0 | 370 | July 20, 2020 | |
which platform support the FP16? | 2 | 3356 | October 12, 2021 | |
Unable to run with half precision on Nvidia GTX 1080 | 3 | 1266 | October 10, 2018 | |
FP16 support on gtx 1060 and 1080 | 14 | 25400 | May 19, 2021 | |
the official info of various models of GPU support what kind of accelerate mode | 1 | 693 | April 30, 2019 | |
Is TensorRT 1.0 supported on GTX 1080? | 0 | 1937 | April 29, 2017 | |
Tensor Flow with GPU support for GTX 1650 max Q | 1 | 835 | April 10, 2023 | |
Check device supports FP16 | 1 | 1211 | April 5, 2022 | |
AttributeError: Specified FP16 but not supported on platform | 3 | 908 | October 12, 2021 | |
TensoRT convewrsion in bfloat16 | 3 | 485 | February 1, 2024 |