Skip to content
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

Why does Building CUDA_BEVFusion asks for libcublas.so.12, and not 11? #293

Open
Tony-syr opened this issue Nov 1, 2024 · 1 comment
Open

Comments

@Tony-syr
Copy link

Tony-syr commented Nov 1, 2024

In the README of the project CUDA_BEVFusion, the wrote "The data in the performance table was obtained by us on the Nvidia Orin platform, using TensorRT-8.6, cuda-11.4 and cudnn8.6 statistics."
when I try to build it with Cuda 11.4 and tensorRT 8.5.2, it askes for the libcublas.so.12, which is part of Cuda-12,
What is wrong in my code
My machine is jetson AGX orin, aarch64
L4T: 35.3.1
ubuntu 20.24
JetPack: 5.1.1

python 3.8
CUDA: 11.4.314
TensorRT: 8.5.2.2

Is there anything wrong with the documentation, how to fix the problem

@Tony-syr
Copy link
Author

Tony-syr commented Nov 1, 2024

I feel that there is some mistakes in the documentation of CUDA_BEVFusion project , because TensorRT 8.6 with Cuda 11.4 is not supported for jetson orin until now. the supported one is Cuda 12 with tensorrt 8.6.
I'm I right?

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

1 participant