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

Brandon/cast unquantized flux to bfloat16 #6815

Merged
merged 5 commits into from
Sep 5, 2024
Merged

Brandon/cast unquantized flux to bfloat16 #6815

merged 5 commits into from
Sep 5, 2024

Commits on Sep 5, 2024

  1. Cast tensors in unquantized flux models to bfloat16 during loading

    @brandonrising
    brandonrising committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    991d264 View commit details
    Browse the repository at this point in the history

  2. Update flux transformer loader to more efficiently use and release me… 

    …mory during upcasting
    @brandonrising
    brandonrising committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    8150a58 View commit details
    Browse the repository at this point in the history

  3. Add comment explaining the cache make room call

    @brandonrising
    brandonrising committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    289ee12 View commit details
    Browse the repository at this point in the history

  4. Remove dependency of asizeof

    @brandonrising
    brandonrising committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    816aac8 View commit details
    Browse the repository at this point in the history

  5. Simplify flux model dtype conversion in model loader

    @brandonrising
    brandonrising committed Sep 5, 2024
    Configuration menu
    Copy the full SHA
    f08e942 View commit details
    Browse the repository at this point in the history