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

[FEAT] Add custom CUDA tinygemm unpacker #415

Merged
merged 21 commits into from
Jul 4, 2024
Merged

[FEAT] Add custom CUDA tinygemm unpacker #415

merged 21 commits into from
Jul 4, 2024

Commits on Jun 21, 2024

  1. add unpack cuda

    @jeromeku
    jeromeku committed Jun 21, 2024
    Configuration menu
    Copy the full SHA
    dc5b10f View commit details
    Browse the repository at this point in the history

  2. add tests

    @jeromeku
    jeromeku committed Jun 21, 2024
    Configuration menu
    Copy the full SHA
    fff3e8a View commit details
    Browse the repository at this point in the history

  3. fix tests

    @jeromeku
    jeromeku committed Jun 21, 2024
    Configuration menu
    Copy the full SHA
    39f23cf View commit details
    Browse the repository at this point in the history

Commits on Jun 23, 2024

  1. refactor tinygemm unpacking kernel

    @jeromeku
    jeromeku committed Jun 23, 2024
    Configuration menu
    Copy the full SHA
    e41b682 View commit details
    Browse the repository at this point in the history

  2. add dequant

    @jeromeku
    jeromeku committed Jun 23, 2024
    Configuration menu
    Copy the full SHA
    3a3d788 View commit details
    Browse the repository at this point in the history

  3. add additional dequant check

    @jeromeku
    jeromeku committed Jun 23, 2024
    Configuration menu
    Copy the full SHA
    a2ca149 View commit details
    Browse the repository at this point in the history

Commits on Jun 27, 2024

  1. update tinygemm dequantize test

    @jeromeku
    jeromeku committed Jun 27, 2024
    Configuration menu
    Copy the full SHA
    052d482 View commit details
    Browse the repository at this point in the history

  2. correct dequant kernel logic

    @jeromeku
    jeromeku committed Jun 27, 2024
    Configuration menu
    Copy the full SHA
    18c505f View commit details
    Browse the repository at this point in the history

  3. clean up kernel

    @jeromeku
    jeromeku committed Jun 27, 2024
    Configuration menu
    Copy the full SHA
    d831a5e View commit details
    Browse the repository at this point in the history

Commits on Jun 28, 2024

  1. update dequantize kernel tests

    @jeromeku
    jeromeku committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    48a8062 View commit details
    Browse the repository at this point in the history

  2. rename kernel ops to tensor_core_tiled_layout

    @jeromeku
    jeromeku committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    279b79a View commit details
    Browse the repository at this point in the history

  3. add renamed kernel source

    @jeromeku
    jeromeku committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    b6ad9f7 View commit details
    Browse the repository at this point in the history

  4. add back test_aot_dispatch opcheck

    @jeromeku
    jeromeku committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    612d8e3 View commit details
    Browse the repository at this point in the history

Commits on Jul 3, 2024

  1. rename innerKTiles to inner_k_tiles

    @jeromeku
    jeromeku committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    9afa73e View commit details
    Browse the repository at this point in the history

  2. add unpack and dequant test

    @jeromeku
    jeromeku committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    f05c720 View commit details
    Browse the repository at this point in the history

  3. additional numerical checks for unpack then dequant

    @jeromeku
    jeromeku committed Jul 3, 2024
    Configuration menu
    Copy the full SHA
    c666a18 View commit details
    Browse the repository at this point in the history

Commits on Jul 4, 2024

  1. rebase test_ops on main

    @jeromeku
    jeromeku committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    e8ca817 View commit details
    Browse the repository at this point in the history

  2. remove commented out code

    @jeromeku
    jeromeku committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    e089ffb View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' into unpack_int4

    @jeromeku
    jeromeku committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    d1bd61b View commit details
    Browse the repository at this point in the history

  4. skip dynamic opcheck unless torch>=2.5

    @jeromeku
    jeromeku committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    75df5f5 View commit details
    Browse the repository at this point in the history

  5. Merge branch 'unpack_int4' of https://github.com/jeromeku/ao into unp… 

    …ack_int4
    @jeromeku
    jeromeku committed Jul 4, 2024
    Configuration menu
    Copy the full SHA
    e90e280 View commit details
    Browse the repository at this point in the history