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

[Tony-syr]

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]

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?