CUDA: use min compute capability of GPUs actually used #2506
Conversation
This file contains hidden or 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
JohannesGaessler
approved these changes
Aug 4, 2023
Collaborator
JohannesGaessler
left a comment
JohannesGaessler
left a comment
There was a problem hiding this comment.
Alternatively you could have used the environmental variable CUDA_VISIBLE_DEVICES to hide the 970.
This was referenced Nov 1, 2023
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
These are my currently installed GPUs:
I found that if I disabled my GTX 970 using
--tensor-split 1,0, I still couldn't use the full compute capability of my Telsa P40. With this change, I am able to benefit from the --mul-mat-q option without physically removing the GTX 970 from my PC, which my displays are connected to.