There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
It is FP16. Please refer to Overview - NVIDIA Docs.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| DINO-FAN_base INT8 model is not faster than FP16 model | 5 | 700 | November 8, 2023 | |
| YoloV4 slower in INT8 than FP16 | 5 | 1513 | June 5, 2021 | |
| Why is' int8 'not as fast as' fp16' | 1 | 565 | February 1, 2021 | |
| Mask-RCNN int8 Version Results in Poor Performance | 37 | 1086 | July 6, 2022 | |
| TRT Engin in INT8 is much slower than FP16 | 4 | 1975 | November 11, 2021 | |
| Is there any layer that fp16 supports but int8 does not？ | 5 | 497 | December 1, 2021 | |
| Data_type problem in generating engine file for DINO model | 7 | 161 | July 12, 2024 | |
| Same inference speed for INT8 and FP16 | 10 | 5881 | October 12, 2021 | |
| The inference speed of yolov5 tensorrt has little difference between int8 and fp16 | 1 | 1529 | September 8, 2022 | |
| Pruning Dino model | 8 | 723 | December 26, 2023 |