Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

torch.compile compatibility #748

Open
anijain2305 opened this issue Sep 9, 2024 · 3 comments
Open

torch.compile compatibility #748

anijain2305 opened this issue Sep 9, 2024 · 3 comments
Labels
enhancement New feature or request performance Running speed & quality question Further information is requested

Comments

@anijain2305
Copy link

I think HuggingFace team made some excellent progress in making generate more torch.compile compatible - huggingface/transformers#29114

It might be worth revisiting torch.compile issues and see if those can be resolved now.

@fumiama fumiama added enhancement New feature or request question Further information is requested performance Running speed & quality labels Sep 10, 2024
@fumiama
Copy link
Member

fumiama commented Sep 10, 2024

That PR has been merged on Feb. The version restriction in ChatTTS is

transformers>=4.41.1

which has included this patch, but nothing changed.

@github-actions github-actions bot added the stale The topic has been ignored for a long time label Oct 11, 2024
@medemi68
Copy link

medemi68 commented Oct 26, 2024

I would love to see if we could get this working or if it is possible to do. On Parler-TTS for example, compilation with reduce overhead brings 4x speed improvement. Right now even with a 4090 I’ve struggled to get good TTFB for realtime streaming. It’d be great if that could be improved somehow.

@github-actions github-actions bot removed the stale The topic has been ignored for a long time label Oct 27, 2024
@fumiama
Copy link
Member

fumiama commented Oct 27, 2024

Now we're implementing vLLM to speed it up.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request performance Running speed & quality question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants