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

HFQuantizer implementation for compressed-tensors library #31704

Merged
merged 42 commits into from
Sep 25, 2024
Merged

HFQuantizer implementation for compressed-tensors library #31704

merged 42 commits into from
Sep 25, 2024

Commits on Jun 5, 2024

  1. Add compressed-tensors HFQuantizer implementation

    Benjamin committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    d695ec3 View commit details
    Browse the repository at this point in the history

  2. flag serializable as False

    Benjamin committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    f468964 View commit details
    Browse the repository at this point in the history

Commits on Jun 10, 2024

  1. run

    @horheynm
    horheynm committed Jun 10, 2024
    Configuration menu
    Copy the full SHA
    41224d3 View commit details
    Browse the repository at this point in the history

  2. revive lines deleted by ruff

    @horheynm
    horheynm committed Jun 10, 2024
    Configuration menu
    Copy the full SHA
    b61bfb9 View commit details
    Browse the repository at this point in the history

Commits on Jun 11, 2024

  1. fixes to load+save from sparseml, edit config to quantization_config,… 

    … and load back
    @horheynm
    horheynm committed Jun 11, 2024
    Configuration menu
    Copy the full SHA
    ff8f1c5 View commit details
    Browse the repository at this point in the history

  2. address satrat comment

    @horheynm
    horheynm committed Jun 11, 2024
    Configuration menu
    Copy the full SHA
    c1cb55d View commit details
    Browse the repository at this point in the history

Commits on Jun 12, 2024

  1. compressed_tensors to compressed-tensors and revert back is_serializable

    @horheynm
    horheynm committed Jun 12, 2024
    Configuration menu
    Copy the full SHA
    ef9d3f1 View commit details
    Browse the repository at this point in the history

  2. rename quant_method from sparseml to compressed-tensors

    @horheynm
    horheynm committed Jun 12, 2024
    Configuration menu
    Copy the full SHA
    117d050 View commit details
    Browse the repository at this point in the history

  3. tests

    @horheynm
    horheynm committed Jun 12, 2024
    Configuration menu
    Copy the full SHA
    1901c3e View commit details
    Browse the repository at this point in the history

Commits on Jun 13, 2024

  1. edit tests

    @horheynm
    horheynm committed Jun 13, 2024
    Configuration menu
    Copy the full SHA
    3ca270d View commit details
    Browse the repository at this point in the history

Commits on Jun 28, 2024

  1. clean up tests

    Benjamin committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    9a14b09 View commit details
    Browse the repository at this point in the history

  2. make style

    Benjamin committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    ec59052 View commit details
    Browse the repository at this point in the history

  3. cleanup

    Benjamin committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    520ded8 View commit details
    Browse the repository at this point in the history

  4. cleanup

    Benjamin committed Jun 28, 2024
    Configuration menu
    Copy the full SHA
    7dec8fc View commit details
    Browse the repository at this point in the history

Commits on Jul 25, 2024

  1. Merge branch 'main' into compressed-tensors-quantizer

    @bfineran
    bfineran authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    afb550d View commit details
    Browse the repository at this point in the history

  2. add test skip for when compressed tensors is not installed

    Benjamin committed Jul 25, 2024
    Configuration menu
    Copy the full SHA
    d9b3660 View commit details
    Browse the repository at this point in the history

  3. remove pydantic import + style

    Benjamin committed Jul 25, 2024
    Configuration menu
    Copy the full SHA
    e51ac59 View commit details
    Browse the repository at this point in the history

  4. delay torch import in test

    Benjamin committed Jul 25, 2024
    Configuration menu
    Copy the full SHA
    ccb5442 View commit details
    Browse the repository at this point in the history

Commits on Jul 30, 2024

  1. initial docs

    Benjamin committed Jul 30, 2024
    Configuration menu
    Copy the full SHA
    bfd9220 View commit details
    Browse the repository at this point in the history

  2. update main init for compressed tensors config

    Benjamin committed Jul 30, 2024
    Configuration menu
    Copy the full SHA
    71a80f9 View commit details
    Browse the repository at this point in the history

  3. make fix-copies

    Benjamin committed Jul 30, 2024
    Configuration menu
    Copy the full SHA
    547f9cc View commit details
    Browse the repository at this point in the history

Commits on Jul 31, 2024

  1. docstring

    Benjamin committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    8acbc09 View commit details
    Browse the repository at this point in the history

  2. remove fill_docstring

    Benjamin committed Jul 31, 2024
    Configuration menu
    Copy the full SHA
    eaa5f20 View commit details
    Browse the repository at this point in the history

Commits on Aug 6, 2024

  1. Apply suggestions from code review 

    Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
    @bfineran @SunMarc
    bfineran and SunMarc authored Aug 6, 2024
    Configuration menu
    Copy the full SHA
    4ba75fb View commit details
    Browse the repository at this point in the history

  2. review comments

    Benjamin committed Aug 6, 2024
    Configuration menu
    Copy the full SHA
    94ea0d3 View commit details
    Browse the repository at this point in the history

  3. review comments

    Benjamin committed Aug 6, 2024
    Configuration menu
    Copy the full SHA
    c48840d View commit details
    Browse the repository at this point in the history

Commits on Aug 19, 2024

  1. Merge branch 'main' into compressed-tensors-quantizer

    @bfineran
    bfineran authored Aug 19, 2024
    Configuration menu
    Copy the full SHA
    ab74d26 View commit details
    Browse the repository at this point in the history

Commits on Aug 20, 2024

  1. comments - suppress warnings on state dict load, tests, fixes

    Benjamin committed Aug 20, 2024
    Configuration menu
    Copy the full SHA
    2ecf711 View commit details
    Browse the repository at this point in the history

Commits on Aug 22, 2024

  1. bug-fix - remove unnecessary call to apply quant lifecycle

    Benjamin committed Aug 22, 2024
    Configuration menu
    Copy the full SHA
    e1ae504 View commit details
    Browse the repository at this point in the history

Commits on Aug 30, 2024

  1. run_compressed compatability

    Sara Adkins committed Aug 30, 2024
    Configuration menu
    Copy the full SHA
    ea9e927 View commit details
    Browse the repository at this point in the history

Commits on Sep 3, 2024

  1. revert changes not needed for compression

    Sara Adkins committed Sep 3, 2024
    Configuration menu
    Copy the full SHA
    1c3ad5c View commit details
    Browse the repository at this point in the history

  2. no longer need unexpected keys fn

    Sara Adkins committed Sep 3, 2024
    Configuration menu
    Copy the full SHA
    aa1a4f9 View commit details
    Browse the repository at this point in the history

  3. unexpected keys not needed either

    Sara Adkins committed Sep 3, 2024
    Configuration menu
    Copy the full SHA
    81a13dd View commit details
    Browse the repository at this point in the history

Commits on Sep 9, 2024

  1. Apply suggestions from code review 

    Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
    @Satrat @SunMarc
    Satrat and SunMarc authored Sep 9, 2024
    Configuration menu
    Copy the full SHA
    f53d7b9 View commit details
    Browse the repository at this point in the history

  2. add to_diff_dict

    Sara Adkins committed Sep 9, 2024
    Configuration menu
    Copy the full SHA
    d8f7073 View commit details
    Browse the repository at this point in the history

Commits on Sep 11, 2024

  1. update docs and expand testing

    Sara Adkins committed Sep 11, 2024
    Configuration menu
    Copy the full SHA
    c4fbf70 View commit details
    Browse the repository at this point in the history

Commits on Sep 17, 2024

  1. Merge remote-tracking branch 'upstream/main' into compressed-tensors-… 

    …quantizer
    Sara Adkins committed Sep 17, 2024
    Configuration menu
    Copy the full SHA
    1992a88 View commit details
    Browse the repository at this point in the history

Commits on Sep 18, 2024

  1. Update _toctree.yml with compressed-tensors

    @Satrat
    Satrat authored Sep 18, 2024
    Configuration menu
    Copy the full SHA
    298a638 View commit details
    Browse the repository at this point in the history

Commits on Sep 23, 2024

  1. Update src/transformers/utils/quantization_config.py 

    Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
    @Satrat @ArthurZucker
    Satrat and ArthurZucker authored Sep 23, 2024
    Configuration menu
    Copy the full SHA
    3cb4415 View commit details
    Browse the repository at this point in the history

Commits on Sep 24, 2024

  1. Merge branch 'main' into compressed-tensors-quantizer

    @dsikka
    dsikka authored Sep 24, 2024
    Configuration menu
    Copy the full SHA
    a943157 View commit details
    Browse the repository at this point in the history

  2. update doc

    @dsikka
    dsikka committed Sep 24, 2024
    Configuration menu
    Copy the full SHA
    64f475a View commit details
    Browse the repository at this point in the history

  3. add note about saving a loaded model

    @dsikka
    dsikka committed Sep 24, 2024
    Configuration menu
    Copy the full SHA
    fabe8a3 View commit details
    Browse the repository at this point in the history