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

[Model] 1.58bits BitNet Model Support #7725

Open
wants to merge 27 commits into
base: main
Choose a base branch
from
Open

[Model] 1.58bits BitNet Model Support #7725

wants to merge 27 commits into from

Commits on Jul 1, 2024

  1. Support Repack from GPTQ.

    @LeiWang1999
    LeiWang1999 committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    2be6218 View commit details
    Browse the repository at this point in the history

  2. chore: Remove unused input_size and output_size variables in MarlinLi… 

    …nearMethod constructor
    @LeiWang1999
    LeiWang1999 committed Jul 1, 2024
    Configuration menu
    Copy the full SHA
    b92de92 View commit details
    Browse the repository at this point in the history

Commits on Jul 16, 2024

  1. Support BitNet Model for 1.58bits.

    @LeiWang1999
    LeiWang1999 committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    71ea469 View commit details
    Browse the repository at this point in the history

  2. Lint Fix

    @LeiWang1999
    LeiWang1999 committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    dfa6b2f View commit details
    Browse the repository at this point in the history

  3. lint fix

    @LeiWang1999
    LeiWang1999 committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    8d2c635 View commit details
    Browse the repository at this point in the history

  4. Lint Fix for line length

    @LeiWang1999
    LeiWang1999 committed Jul 16, 2024
    Configuration menu
    Copy the full SHA
    41bb18e View commit details
    Browse the repository at this point in the history

Commits on Jul 17, 2024

  1. Support Loading 1.58B Model with BitBLAS Format

    @LeiWang1999
    LeiWang1999 committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    29ac34d View commit details
    Browse the repository at this point in the history

Commits on Jul 19, 2024

  1. Improve performance for bitnet

    @LeiWang1999
    LeiWang1999 committed Jul 19, 2024
    Configuration menu
    Copy the full SHA
    7f69aef View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' of https://github.com/vllm-project/vllm into bitb… 

    …las-intg
    @LeiWang1999
    LeiWang1999 committed Jul 19, 2024
    Configuration menu
    Copy the full SHA
    01a789a View commit details
    Browse the repository at this point in the history

  3. fix lm_head for gptq model refactor

    @LeiWang1999
    LeiWang1999 committed Jul 19, 2024
    Configuration menu
    Copy the full SHA
    a973123 View commit details
    Browse the repository at this point in the history

  4. linx fix

    @LeiWang1999
    LeiWang1999 committed Jul 19, 2024
    Configuration menu
    Copy the full SHA
    aea1f4c View commit details
    Browse the repository at this point in the history

Commits on Aug 13, 2024

  1. handle compressed scale weight.

    @LeiWang1999
    LeiWang1999 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    17128d5 View commit details
    Browse the repository at this point in the history

  2. lint fix

    @LeiWang1999
    LeiWang1999 committed Aug 13, 2024
    Configuration menu
    Copy the full SHA
    1741ed4 View commit details
    Browse the repository at this point in the history

Commits on Aug 15, 2024

  1. remove partial weight load for sw

    @LeiWang1999
    LeiWang1999 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    726a1f7 View commit details
    Browse the repository at this point in the history

  2. apply torch compile for uncompressed weight.

    @LeiWang1999
    LeiWang1999 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    68c8052 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' of https://github.com/vllm-project/vllm into bitb… 

    …las-intg
    @LeiWang1999
    LeiWang1999 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    6eb2870 View commit details
    Browse the repository at this point in the history

  4. merge bug fix

    @LeiWang1999
    LeiWang1999 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    52418ef View commit details
    Browse the repository at this point in the history

  5. lint fix

    @LeiWang1999
    LeiWang1999 committed Aug 15, 2024
    Configuration menu
    Copy the full SHA
    a15ba12 View commit details
    Browse the repository at this point in the history

Commits on Aug 18, 2024

  1. fix torch compile issue

    @LeiWang1999
    LeiWang1999 committed Aug 18, 2024
    Configuration menu
    Copy the full SHA
    53babae View commit details
    Browse the repository at this point in the history

Commits on Aug 20, 2024

  1. bug fix.

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    40a4e53 View commit details
    Browse the repository at this point in the history

  2. BENCHMARK SCRIPTS

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    d316a87 View commit details
    Browse the repository at this point in the history

  3. Merge branch 'main' of https://github.com/vllm-project/vllm into bitb… 

    …las-intg
    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    4d40275 View commit details
    Browse the repository at this point in the history

  4. Implement Test

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    bffc05b View commit details
    Browse the repository at this point in the history

  5. lint fix

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    8b0972b View commit details
    Browse the repository at this point in the history

  6. install bitblas by default to pass the doc gen.

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    8e1a7e8 View commit details
    Browse the repository at this point in the history

  7. hide the bitblas import

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    7fbbccf View commit details
    Browse the repository at this point in the history

  8. import fix

    @LeiWang1999
    LeiWang1999 committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    c487e69 View commit details
    Browse the repository at this point in the history