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

[FIX] Padding infeatures/outfeatures for exllama, exllama v2, and marlin #98

Merged
merged 19 commits into from
Jun 29, 2024
Merged

[FIX] Padding infeatures/outfeatures for exllama, exllama v2, and marlin #98

merged 19 commits into from
Jun 29, 2024

Commits on Jun 28, 2024

  1. fix padding

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    8031585 View commit details
    Browse the repository at this point in the history

  2. fix padding

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    44b97a6 View commit details
    Browse the repository at this point in the history

  3. store original in/out features

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    6717991 View commit details
    Browse the repository at this point in the history

  4. fix bad var reference

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    6909080 View commit details
    Browse the repository at this point in the history

  5. shorter var name

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    3289743 View commit details
    Browse the repository at this point in the history

  6. limit bitblas convert to use 1 thread

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    1c064fd View commit details
    Browse the repository at this point in the history

  7. ruff

    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    12552e4 View commit details
    Browse the repository at this point in the history

  8. fix qlinear_exllama pack

    LRL-ModelCloud committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    c4b9ea2 View commit details
    Browse the repository at this point in the history

  9. revert qliner_marlin change

    LRL-ModelCloud committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    8670dc4 View commit details
    Browse the repository at this point in the history

  10. cleanup code

    LRL-ModelCloud committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    f37b4ae View commit details
    Browse the repository at this point in the history

  11. plan b: init with original shape, then model load, then do padding/re… 

    …size in post_init
    @Qubitium
    Qubitium committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    d78d75f View commit details
    Browse the repository at this point in the history

Commits on Jun 29, 2024

  1. Merge branch 'main' into padding

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    776b620 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into padding

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    3b57766 View commit details
    Browse the repository at this point in the history

  3. fix g_idx post_init

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    105b6a9 View commit details
    Browse the repository at this point in the history

  4. const var reformat to all caps

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    a96ef4d View commit details
    Browse the repository at this point in the history

  5. fix ( -> [

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    90f3f54 View commit details
    Browse the repository at this point in the history

  6. padding the x that passes in forward

    LRL-ModelCloud committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    4189817 View commit details
    Browse the repository at this point in the history

  7. comments/todo

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    32dec09 View commit details
    Browse the repository at this point in the history

  8. comments

    @Qubitium
    Qubitium committed Jun 29, 2024
    Configuration menu
    Copy the full SHA
    3c2ba94 View commit details
    Browse the repository at this point in the history