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

[CPU EP] Refactor MatMulNBits to decouple type implementation #22140

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

[CPU EP] Refactor MatMulNBits to decouple type implementation #22140

wants to merge 6 commits into from
+410 −260

Commits on Sep 18, 2024

  1. refactored MatMulNBits compute to separate implementation for differe… 

    …nt types
    @fajin-corp
    fajin-corp committed Sep 18, 2024
    Configuration menu
    Copy the full SHA
    390678d View commit details
    Browse the repository at this point in the history

  2. move compute type to class fields

    @fajin-corp
    fajin-corp committed Sep 18, 2024
    Configuration menu
    Copy the full SHA
    2c53218 View commit details
    Browse the repository at this point in the history

Commits on Sep 19, 2024

  1. add specialization for repack scale

    @fajin-corp
    fajin-corp committed Sep 19, 2024
    Configuration menu
    Copy the full SHA
    e3a5b92 View commit details
    Browse the repository at this point in the history

  2. fix build

    @fajin-corp
    fajin-corp committed Sep 19, 2024
    Configuration menu
    Copy the full SHA
    b37cd5c View commit details
    Browse the repository at this point in the history

  3. fix ut

    @fajin-corp
    fajin-corp committed Sep 19, 2024
    Configuration menu
    Copy the full SHA
    c08769a View commit details
    Browse the repository at this point in the history

  4. fix linux build

    @fajin-corp
    fajin-corp committed Sep 19, 2024
    Configuration menu
    Copy the full SHA
    b5799bf View commit details
    Browse the repository at this point in the history