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

Create report for Autoquant #855

Open
drisspg opened this issue Sep 9, 2024 · 0 comments
Open

Create report for Autoquant #855

drisspg opened this issue Sep 9, 2024 · 0 comments

Comments

@drisspg
Copy link
Contributor

drisspg commented Sep 9, 2024

Summary

Autoquant will iterate through a user module and identify all linear dtype + shapes as well as execution time for different quantization routines. This information is baked into the final model output but it is not easily viewable.

We want to add an api for exposing this information.

We should add the option to generate human readable reports for a given autoquant run on a model. This will be useful for identifying strange autoquant behavior - why was quantX chosen over quantY.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant