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

Fix layer_normalize gradients #3001

Merged
merged 8 commits into from
Sep 1, 2024
Merged

Fix layer_normalize gradients #3001

merged 8 commits into from
Sep 1, 2024

Commits on Aug 28, 2024

  1. Fix layer_normalize gradients

    @arrufat
    arrufat committed Aug 28, 2024
    Configuration menu
    Copy the full SHA
    4c6e4bd View commit details
    Browse the repository at this point in the history

Commits on Aug 30, 2024

  1. fix layer_norm CPU

    @arrufat
    arrufat committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    60f29fc View commit details
    Browse the repository at this point in the history

  2. attempt to fix the cuda version

    @arrufat
    arrufat committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    6118f80 View commit details
    Browse the repository at this point in the history

Commits on Aug 31, 2024

  1. fix gamma_grad and beta_grad

    @arrufat
    arrufat committed Aug 31, 2024
    Configuration menu
    Copy the full SHA
    cf4af98 View commit details
    Browse the repository at this point in the history

  2. update cuda test

    @arrufat
    arrufat committed Aug 31, 2024
    Configuration menu
    Copy the full SHA
    e807c58 View commit details
    Browse the repository at this point in the history

  3. use a block of size 1 to avoid race conditions

    @arrufat
    arrufat committed Aug 31, 2024
    Configuration menu
    Copy the full SHA
    048818a View commit details
    Browse the repository at this point in the history

Commits on Sep 1, 2024

  1. improve the speed of CUDA path of layer_norm

    @arrufat
    arrufat committed Sep 1, 2024
    Configuration menu
    Copy the full SHA
    dd1cdc6 View commit details
    Browse the repository at this point in the history

  2. improve the speed of CUDA path of layer_norm

    @arrufat
    arrufat committed Sep 1, 2024
    Configuration menu
    Copy the full SHA
    c0627a5 View commit details
    Browse the repository at this point in the history