Mo Shahdloo comments

Repositories
Issues
Comments

Results 2 comments of


                                            Mo Shahdloo

FP16 Accuracy failure of TensorRT 8.6.3 when running trtexec built engine on GPU RTX4090

> [!] Model type: engine could not be converted to an ONNX model. This will go away if you use golden inputs/outputs produced separately, rather than passing `--onnxrt` to check...

Does TensorRT have plugin for onnx's DynamicQuantizeLinear?

Hi. I would like to ask you to reopen this, because I can't get my head around how `tensorflow-quantization` referenced here: > Ref https://github.com/NVIDIA/TensorRT/tree/release/10.1/tools/tensorflow-quantization @myunuro can be a follow up...