Added extra steps to update the Cudnnn DLL found in the Torch packages #4459
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
I added extra steps to update the Cudnnn DLL found in the Torch package because it wasn't optimised or didn't use the lastest version. So manually updating it can speed up iteration but the result might differ from each card. Exemple i passed from 3 it/s to a steady 20 it/s.
Keerigan45
requested review from
lstein,
blessedcoolant,
hipsterusername and
Millu
as code owners
|
Maybe also add if one should download the CUDA 11.X or CUDA 12.X version of CUDNN because that is something one is asked to choose from before downloading. |
|
https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html May add this link and ask to just download the 11x version if their architecture doesn't show up. Or they can try both if they got time to see which version works better. |
Millu
approved these changes
Sep 6, 2023
Millu
suggested changes
Sep 6, 2023
Added Extra step and clarification on how to choose between 11x or 12x update for Cudnnn dll
Millu
approved these changes
Sep 7, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I added extra steps to update the Cudnnn DLL found in the Torch package because it wasn't optimised or didn't use the lastest version. So manually updating it can speed up iteration but the result might differ from each card. Exemple i passed from 3 it/s to a steady 20 it/s.
What type of PR is this? (check all applicable)
Have you discussed this change with the InvokeAI team?
Have you updated all relevant documentation?
Description
Related Tickets & Documents
QA Instructions, Screenshots, Recordings
Added/updated tests?
have not been included
[optional] Are there any post deployment tasks we need to perform?