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

Rationale behind converting proj_out of FluxSingleTransformerBlock to ConcatLinear #43

Open
vinovo opened this issue Jan 29, 2025 · 0 comments
Labels
question Further information is requested svdquant

Comments

@vinovo
Copy link

vinovo commented Jan 29, 2025

in this code

We can see only proj_out of FluxSingleTransformerBlock are converted to ConcatLinear with only a single split [module.proj_out.out_features].

Can anyone help explain the reasoning behind this?

  • Why we only cares about proj_out of FluxSingleTransformerBlock. Should this operation be performed on all transformer based diffusion models?
  • Why do we only care to create one single split? What is the benefit of using ConcatLinear?

Thank you in advance.

@lmxyy lmxyy added question Further information is requested svdquant labels Jan 29, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested svdquant
Projects
None yet
Development

No branches or pull requests

2 participants