Skip to content

Failed to build engine parser #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
next-gen-machine opened this issue Jul 13, 2023 · 5 comments
Open

Failed to build engine parser #1

next-gen-machine opened this issue Jul 13, 2023 · 5 comments

Comments

@next-gen-machine
Copy link

Hii, when I execute ./bevdemo ../configure.yaml , got error

ERROR: 3: [runtime.cpp::deserializeCudaEngine::36] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::deserializeCudaEngine::36, condition: (blob) != nullptr
)
ERROR: Failed to build engine parser!
free(): double free detected in tcache 2
Aborted (core dumped)

Please resolve it

@LCH1238
Copy link
Owner

LCH1238 commented Jul 14, 2023

Hii, when I execute ./bevdemo ../configure.yaml , got error

ERROR: 3: [runtime.cpp::deserializeCudaEngine::36] Error Code 3: API Usage Error (Parameter check failed at: runtime/rt/runtime.cpp::deserializeCudaEngine::36, condition: (blob) != nullptr ) ERROR: Failed to build engine parser! free(): double free detected in tcache 2 Aborted (core dumped)

Please resolve it

Please check if the path name in your configure.yaml is consistent with your engine file name!
image

@next-gen-machine
Copy link
Author

Thanks a lot. It is working.
I have one question. Can I use tensorrt engine build on x86 architecture for inference on aarch64 architecture or I have to build create engine on aarch64 architecture using this repository?

@LCH1238
Copy link
Owner

LCH1238 commented Jul 14, 2023

Thanks a lot. It is working. I have one question. Can I use tensorrt engine build on x86 architecture for inference on aarch64 architecture or I have to build create engine on aarch64 architecture using this repository?

TensorRT 8.6 and previous versions do not allow this. I suggest you to create a engine on aarch64 architecture.

@next-gen-machine
Copy link
Author

Hii, Thanks a lot for your quick replies. Can you provide C++ API code for export_engine, because my Drive AGX Orin board supports only C++ API of TensorRT (TensorRT Version 8.5). (DRIVE OS 6.0.6 on Drive AGX Orin board)
Or
If you have any method to install TensorRT Python package for DRIVE AGX Orin, it would be very helpful if you suggest that method.
Thanks in advance.

@LCH1238
Copy link
Owner

LCH1238 commented Jul 17, 2023

Hii, Thanks a lot for your quick replies. Can you provide C++ API code for export_engine, because my Drive AGX Orin board supports only C++ API of TensorRT (TensorRT Version 8.5). (DRIVE OS 6.0.6 on Drive AGX Orin board) Or If you have any method to install TensorRT Python package for DRIVE AGX Orin, it would be very helpful if you suggest that method. Thanks in advance.

I didn't write this code. I don't have DRIVE AGX Orin, you can write a C++ code yourself.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants