Zero Zeng

You can send a private Google drive link here and I'll request for access, P.S. the email address would be similar to my github name but I don't want to...

Requested access, please reply after you grant the access(so that I can get the notification), thanks!

I ran `mpirun -np 4 trtexec --loadEngine=resnet50_1x1024x1024.trt --useCudaGraph --streams=4 --iterations=1000000 --device=1` for over 30 mins and didn't reproduce the issue. Could you please try: 1. Use our official TensorRT docker...

I can reproduce the error, Filed internal bug 4479712 to track this.

Looks like a bug, could you please provide the onnx and reproduce command?

Is this the error you see? ``` [01/07/2024-12:46:59] [I] [TRT] ---------------------------------------------------------------- [01/07/2024-12:46:59] [I] Finished parsing network model. Parse time: 0.0404419 [01/07/2024-12:46:59] [I] FP32 and INT8 precisions have been specified -...

Thanks for the clarification, filed internal bug 4450368 to track this.

@ttyio ^ ^

I've requested access. Could you please try this with trtexec? like `trtexec --onnx=model.onnx`. If possible, it would be great if you can test latest 9.1 release or on other newer...

Looks like an env issue, I try to build with our tensorrt official container and the build suceess, maybe you can try it too.