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

Add cache rotation inputs and CPU kernel implementation for cache rotation #27088

Draft
wants to merge 14 commits into
base: master
Choose a base branch
from
Draft

Add cache rotation inputs and CPU kernel implementation for cache rotation #27088

wants to merge 14 commits into from
+817 −45

Commits on Nov 11, 2024

  1. Add cache rotation inputs in transformations, CPU and GPU plugins 

    # Conflicts:
#	src/core/src/op/paged_attention.cpp
    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    eb19902 View commit details
    Browse the repository at this point in the history

  2. Fix missing internal dimension

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    9302ada View commit details
    Browse the repository at this point in the history

  3. Fixes

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    65c26e9 View commit details
    Browse the repository at this point in the history

  4. Apply comments

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    8de94e4 View commit details
    Browse the repository at this point in the history

  5. Use llama-style rotation

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    f6e04a8 View commit details
    Browse the repository at this point in the history

  6. Implement AVX512 version w/ intrinsics

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    870fb6d View commit details
    Browse the repository at this point in the history

  7. Refactor the kernel

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    a2c2d0a View commit details
    Browse the repository at this point in the history

  8. Add AVX2 impl

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    072c13b View commit details
    Browse the repository at this point in the history

  9. Add SW impl reference unit test

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    452736d View commit details
    Browse the repository at this point in the history

  10. Add HW impl block tests

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    929e5ba View commit details
    Browse the repository at this point in the history

  11. Add chunk tests

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    c97cd62 View commit details
    Browse the repository at this point in the history

  12. Fix tests

    @vshampor
    vshampor committed Nov 11, 2024
    Configuration menu
    Copy the full SHA
    7722675 View commit details
    Browse the repository at this point in the history

Commits on Nov 12, 2024

  1. Add testing for chunk rotation in FP16 and BF16

    @vshampor
    vshampor committed Nov 12, 2024
    Configuration menu
    Copy the full SHA
    ed46cfe View commit details
    Browse the repository at this point in the history

Commits on Nov 13, 2024

  1. Fix bugs

    @vshampor
    vshampor committed Nov 13, 2024
    Configuration menu
    Copy the full SHA
    8af57a6 View commit details
    Browse the repository at this point in the history