my device :
GPU: V100
ubuntu:16.04
CUDA;10
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Is TensorRT 1.0 supported on GTX 1080? | 0 | 2117 | April 29, 2017 | |
| TensorRT 2.1.2 supports INT8 inference on GTX1080 and Pascal TitanX? | 1 | 1093 | September 4, 2017 | |
| Excuse me, does the 3060Ti graphics card support TensorRT int8 quantization? | 1 | 1556 | June 23, 2022 | |
| platformHasFastInt8 returns true on Geforce GTX1060 | 2 | 1642 | March 31, 2020 | |
| TensorRT with Tensorflow Evaluation on 1080Ti | 1 | 2633 | December 11, 2019 | |
| Minimum compute capability for INT8 optimization? | 2 | 954 | January 14, 2021 | |
| Tensorrt inference runs slower in RTX4090 than RTX 3090 Ti | 3 | 2333 | January 10, 2023 | |
| INT8 cublasGemmEx support on Tegra X2 and Tesla P100 | 4 | 2016 | October 17, 2017 | |
| Turing Tensor core int4 operation | 3 | 2996 | December 11, 2018 | |
| FP16 --half=true option doesn't work on GTX 1080 TI although it runs ./sample_int8 INT8 | 2 | 5221 | August 23, 2017 |