TRT support for CUDA11.1?

Description

When will TensorRT support CUDA 11.1?
The TRT DSOs are pointing to the CUDA 11.0 version of libnvrtc.so.

Environment

TensorRT Version: 7.2.0.14rc
GPU Type: V100, A100
Nvidia Driver Version: 455.23.05
CUDA Version: 11.1
CUDNN Version: 8.0.4
Operating System + Version: Ubuntu18.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Hi @seberino,

Please stay tuned for announcement related to TRT 7.2 support for CUDA 11.1.
Request you to follow TRT dev forum or NVIDIA website for updates.

Thanks

Hi,

I am a bit confused on TRT 7.2.2 support matrix:
https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#platform-matrix
It says TRT 7.2.2 supports cudNN 8.0.5 and cuda11.2.

However the cudNN support matrix:
https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html#cudnn-versions-804-805
It says cudNN 8.0.5 supports cuda11.1 only.

Can I install a working TRT 7.2.2:
https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/7.2.2/zip/TensorRT-7.2.2.3.Windows10.x86_64.cuda-11.1.cudnn8.0.zip
with cudNN 8.05 and cuda11.2 ?

Regards,
Csaba