Internal Error ([HostToDeviceCopy] requires bool I/O but node can not be handled by Myelin. Operatio

Description

A clear and concise description of the bug or issue.

Environment

TensorRT Version: 8.4.2.4
GPU Type: rtx3060
Nvidia Driver Version: 525.147.05
CUDA Version: 11.4
CUDNN Version: 8.9.5
Operating System + Version: ubuntu20.04
Python Version (if applicable): 3.8.4
PyTorch Version (if applicable): 1.10.1

problem description
polygraphy run /home/zzx/VAD/onnx_opti/trans_encoder/bevformerencodertrt.onnx --trt --save-engine=model-04.plan --tactic-sources cublas --load-inputs /home/zzx/VAD/onnx_opti/trans_encoder/custom_inputs.json --verbose

If the command line is followed by ---- trt-outputs mark all, the problem will occur:Internal Error ([HostToDeviceCopy] requires bool I/O but node can not be handled by Myelin.

Hi @1017948396 ,
Can you try the latest TRT release and confirm if you see this issue.
This was a known bug and have been fixed post 8.4
Thanks