add automatic MPS device support #27
Merged
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
|
Thanks for your contribution! |
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Outdated suggestions cannot be applied.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.
Add automatic GPU acceleration for arm-based Apple computers using the MPS device. It should behave the same way as automatic CUDA discovery on Nvidia GPUs.
If "cuda" device is not available, then query
torch.backends.mps.is_available(), and only fall back to cpu if none of them are there.Had to disable this for the CLAP models now, because:
The operator 'aten::upsample_bicubic2d.out' is not currently implemented for the MPS device.It works with the rest.
Also moved the "Audio is mono..." warning in
get_embeddingswhen using Encodec under aself.verbosecheck, otherwise it ends up being very verbose in practice even ifself.verbose==False. :)) Hope that's okay.