Cask Error when using int8, fp32 works fine.

When I create a engine with int8 mode, it raises following error:

[TensorRT] ERROR: …/builder/caskConvolutionBuilder.cpp (737) - Cask Error in createConstants: 13 (canImplement)
[TensorRT] ERROR: …/builder/caskConvolutionBuilder.cpp (737) - Cask Error in createConstants: 13 (canImplement)

If I disable int8 mode, it works fine.

I can’t provide reproduce code because the code and the model isn’t open source.

Hi,

Could you please provide details on the platforms you are using:
o Linux distro and version
o GPU type
o Nvidia driver version
o CUDA version
o CUDNN version
o Python version [if using python]
o Tensorflow and PyTorch version
o TensorRT version
If possible, please share the script & model file to reproduce the issue.

Thanks