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

[GPU] MLP : 2fcs + swiglu fusion #27831

Open
wants to merge 12 commits into
base: master
Choose a base branch
from
Open

[GPU] MLP : 2fcs + swiglu fusion #27831

wants to merge 12 commits into from
+437 −48

Commits on Nov 29, 2024

  1. swiglu_fuse_infra 

    swiglu kernel
working with static kernel only

swiglu : working with dynamic shape only

swiglu works with dynamic shape + static shape

no print

refactor

Fix phi3 crash

Support dynamic quantization path

Fix 1st token regression

Apply only for cldnn

clean up
    @yeonbok
    yeonbok committed Nov 29, 2024
    Configuration menu
    Copy the full SHA
    3ad5ccb View commit details
    Browse the repository at this point in the history

  2. Fix rebase error

    @yeonbok
    yeonbok committed Nov 29, 2024
    Configuration menu
    Copy the full SHA
    a15090e View commit details
    Browse the repository at this point in the history

  3. clean up

    @yeonbok
    yeonbok committed Nov 29, 2024
    Configuration menu
    Copy the full SHA
    ec42903 View commit details
    Browse the repository at this point in the history

  4. cleanup 2

    @yeonbok
    yeonbok committed Nov 29, 2024
    Configuration menu
    Copy the full SHA
    9baad14 View commit details
    Browse the repository at this point in the history

  5. Revert unnecessary fix

    @yeonbok
    yeonbok committed Nov 29, 2024
    Configuration menu
    Copy the full SHA
    7785e9f View commit details
    Browse the repository at this point in the history

Commits on Dec 1, 2024

  1. fix lint error

    @yeonbok
    yeonbok committed Dec 1, 2024
    Configuration menu
    Copy the full SHA
    71e7beb View commit details
    Browse the repository at this point in the history

  2. limit fc swiglu fusion only for fp16 + int4 weight 

    Added unittests
    @yeonbok
    yeonbok committed Dec 1, 2024
    Configuration menu
    Copy the full SHA
    b4146cf View commit details
    Browse the repository at this point in the history

Commits on Dec 2, 2024

  1. Fix crash in cached case

    @yeonbok
    yeonbok committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    68d1813 View commit details
    Browse the repository at this point in the history

  2. Revert "Revert unnecessary fix" 

    This reverts commit 7785e9f.
    @yeonbok
    yeonbok committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    8db24da View commit details
    Browse the repository at this point in the history

  3. fix for OV_GPU_DisableFCFusion=1

    @yeonbok
    yeonbok committed Dec 2, 2024
    Configuration menu
    Copy the full SHA
    afc3b0a View commit details
    Browse the repository at this point in the history

Commits on Dec 3, 2024

  1. Fix unittest

    @yeonbok
    yeonbok committed Dec 3, 2024
    Configuration menu
    Copy the full SHA
    f952237 View commit details
    Browse the repository at this point in the history

  2. fix unittest 2

    @yeonbok
    yeonbok committed Dec 3, 2024
    Configuration menu
    Copy the full SHA
    84482a9 View commit details
    Browse the repository at this point in the history