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.

Sign up for GitHub

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

Jump to bottom

Allow Int4WeightOnlyQuantizer to set different dtype for scales_and_zeros #479

Merged
merged 2 commits into from
Jul 5, 2024
Merged

Allow Int4WeightOnlyQuantizer to set different dtype for scales_and_zeros #479

merged 2 commits into from
Jul 5, 2024

Commits on Jul 5, 2024

  1. Allow Int4WeightOnlyQuantizer to set different dtype for 

    scales_and_zeros

As titled. Currently `Int4WeightOnlyQuantizer` is hardcoded to return
`scales_and_zeros` with dtype `torch.bfloat16`. Adding `dtype` argument
into the flow so that it can be different dtype.
    @larryliu0820
    larryliu0820 committed Jul 5, 2024
    Configuration menu
    Copy the full SHA
    df3b18a View commit details
    Browse the repository at this point in the history

  2. Add comment

    @larryliu0820
    larryliu0820 committed Jul 5, 2024
    Configuration menu
    Copy the full SHA
    f3c320a View commit details
    Browse the repository at this point in the history