Does TensorRT 2.1.2 support INT8 inference on GTX1080 and Pascal TitanX?
I see these two cards are supported of INT8 calculation in PPT S7310 Page 5.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to use int8 inference with JetsonTX2+TensorRT-2.1.2 | 2 | 5342 | October 18, 2021 | |
| About TensorRT2.1 SampleInt8 | 4 | 1139 | October 18, 2021 | |
| Which GPU support INT8? Tesla V100? | 0 | 1275 | June 26, 2019 | |
| Is TensorRT 1.0 supported on GTX 1080? | 0 | 2091 | April 29, 2017 | |
| platformHasFastInt8 returns true on Geforce GTX1060 | 3 | 1595 | October 12, 2021 | |
| Excuse me, does the 3060Ti graphics card support TensorRT int8 quantization? | 1 | 1506 | June 23, 2022 | |
| FP16 --half=true option doesn't work on GTX 1080 TI although it runs ./sample_int8 INT8 | 2 | 5166 | August 23, 2017 | |
| Is there any layer that fp16 supports but int8 does not？ | 5 | 594 | December 1, 2021 | |
| TensorRT with Tensorflow Evaluation on 1080Ti | 1 | 2598 | December 11, 2019 | |
| Minimum compute capability for INT8 optimization? | 2 | 917 | January 14, 2021 |