Update 030_INSTALL_CUDA_AND_ROCM.md

Added Extra step and clarification on how to choose between 11x or 12x update for Cudnnn dll

Author: Keerigan45

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -66,12 +66,16 @@ Runtime Site](https://developer.nvidia.com/nvidia-container-runtime)
 5. Click on Torch directory - e.g., YourInvokeFolderHere\InvokeAI\\.venv\Lib\site-packages\torch
 6. Click on the lib folder - e.g., YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib
 7. Copy everything inside the folder and save it elsewhere as a backup.
-8. Go to https://developer.nvidia.com/cudnn
-9. Log-in Or Create An account
-10. Download the latest version and extract it from the download location
-12. Find the bin folder E\cudnn-windows-x86_64-__Whatever Version__\bin
-13. Copy and paste the 7 .dll files into YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib **Make sure to copy, and not move the files**
-14. If prompted, replace any existing files 
+8. Go to __https://developer.nvidia.com/cudnn__
+9. Login or create an Account. 
+10. Choose the newer version of Cudnnn but __read__ the Important Note  __Important Note:__
+There is two version 11x or 12x for the differents architectures(Turing,Maxwell Etc...) of GPUs.
+You can find which version you should download here note that it's based on your graphics card architecture so for exemple a 4090 use the Ada Lovelace Architecture etc.: __https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html__
+11. Log-in Or Create An account
+12. Download the latest version and extract it from the download location
+13. Find the bin folder E\cudnn-windows-x86_64-__Whatever Version__\bin
+14. Copy and paste the 7 .dll files into YourInvokeFolderHere\\.venv\Lib\site-packages\torch\lib **Make sure to copy, and not move the files**
+15. If prompted, replace any existing files 
 
 **Notes:** 
 * If no change is seen or any issues are encountered, follow the same steps as above and paste the torch/lib backup folder you made earlier and replace it. If you didn't make a backup, you can also uninstall and reinstall torch through the command line to repair this folder.