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

LinearInt8 layer for inference of int8-quantized LLMs and Arm intrinsics #5007

Closed
wants to merge 14 commits into from
Closed

LinearInt8 layer for inference of int8-quantized LLMs and Arm intrinsics #5007

wants to merge 14 commits into from

Commits on Sep 12, 2023

  1. Rebase: Rebase: Rebase: Add custom layer for int8-quantized LLM

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    1436252 View commit details
    Browse the repository at this point in the history

  2. Fix trailing newlines

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    6e8d028 View commit details
    Browse the repository at this point in the history

  3. apply code-format changes

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    3b40f30 View commit details
    Browse the repository at this point in the history

  4. Add more error checking

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    2ecd5af View commit details
    Browse the repository at this point in the history

  5. Add include guard

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    5184b87 View commit details
    Browse the repository at this point in the history

  6. Initial commit for tests

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    e53be3c View commit details
    Browse the repository at this point in the history

  7. Change test function names

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    01f30ec View commit details
    Browse the repository at this point in the history

  8. Add general optimizations

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    52cbc59 View commit details
    Browse the repository at this point in the history

  9. apply code-format changes

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    9426487 View commit details
    Browse the repository at this point in the history

  10. Fix int8 weights being converted into fp16 or bf16

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    d2ce74b View commit details
    Browse the repository at this point in the history

  11. [skip ci] Add a trailing newline?

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    61d6c84 View commit details
    Browse the repository at this point in the history

  12. Remove TODO banner

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    f4e961a View commit details
    Browse the repository at this point in the history

  13. Update documentation

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    6be8196 View commit details
    Browse the repository at this point in the history

  14. Update operators table

    @lrw04
    lrw04 committed Sep 12, 2023
    Configuration menu
    Copy the full SHA
    68b4b2d View commit details
    Browse the repository at this point in the history