Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ModelCloud/GPTQModel
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.9.9
Choose a base ref
...
head repository: ModelCloud/GPTQModel
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.9.10
Choose a head ref
  • 15 commits
  • 32 files changed
  • 6 contributors

Commits on Jul 24, 2024

  1. Update README.md (#293)

    @Qubitium
    Qubitium authored Jul 24, 2024
    Configuration menu
    Copy the full SHA
    93deca9 View commit details
    Browse the repository at this point in the history

  2. being 0.9.10-dev0 cycle (#294)

    @Qubitium
    Qubitium authored Jul 24, 2024
    Configuration menu
    Copy the full SHA
    695f71a View commit details
    Browse the repository at this point in the history

Commits on Jul 25, 2024

  1. set to 40m (#295)

    @CSY-ModelCloud
    CSY-ModelCloud authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    19b52df View commit details
    Browse the repository at this point in the history

  2. [FIX] save_quantized() (#296) 

    * When save_quantized() is called, if the model is loaded quantized model, the QuantLinear used when quantize() is used when saving.

* add unit test

* cleanup

* QuantizeConfig add "runtime_format" field
    @ZX-ModelCloud
    ZX-ModelCloud authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    69c7e71 View commit details
    Browse the repository at this point in the history

  3. [FIX] set the nsample/seqlen according to the actual size of the cali… 

    …bration_dataset. (#297)

* set the nsamples according to the actual size of the calibration_dataset

* set the seqlen according to the actual size of the calibration_dataset.

* cleanup

---------

Co-authored-by: LRL-ModelCloud <[email protected]>
    @LRL2-ModelCloud
    LRL-ModelCloud and LRL2-ModelCloud authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    d7c0c1f View commit details
    Browse the repository at this point in the history

  4. increa perplexity threshold (#299)

    @CSY-ModelCloud
    CSY-ModelCloud authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    102b65c View commit details
    Browse the repository at this point in the history

  5. fix missing self.quantize_config.seqlen (#298) 

    Co-authored-by: LRL-ModelCloud <[email protected]>
    @LRL2-ModelCloud
    LRL-ModelCloud and LRL2-ModelCloud authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    01e4c96 View commit details
    Browse the repository at this point in the history

  6. increase precision in avg_loss and decrease for time taken per module (… 

    …#301)
    @Qubitium
    Qubitium authored Jul 25, 2024
    Configuration menu
    Copy the full SHA
    a30b1f7 View commit details
    Browse the repository at this point in the history

Commits on Jul 26, 2024

  1. [FIX] missing .py files for models using trust_remote (#302) 

    * add save_quant copy py from origin path

* mod clean up

* Rename test_quant_unsupport_transformers.py to test_quant_trust_remote.py

* Update base.py

* Update test_quant_trust_remote.py

---------

Co-authored-by: Qubitium-ModelCloud <[email protected]>
    @PZS-ModelCloud @Qubitium
    PZS-ModelCloud and Qubitium authored Jul 26, 2024
    Configuration menu
    Copy the full SHA
    a046135 View commit details
    Browse the repository at this point in the history

  2. update hf transformers to 4.43.3 (#305)

    @Qubitium
    Qubitium authored Jul 26, 2024
    Configuration menu
    Copy the full SHA
    6f84dd5 View commit details
    Browse the repository at this point in the history

Commits on Jul 28, 2024

  1. [FIX] quantize example (#307)

    LRL-ModelCloud authored Jul 28, 2024
    Configuration menu
    Copy the full SHA
    503c8fa View commit details
    Browse the repository at this point in the history

Commits on Jul 29, 2024

  1. fix typo (#309)

    LRL-ModelCloud authored Jul 29, 2024
    Configuration menu
    Copy the full SHA
    d0a1601 View commit details
    Browse the repository at this point in the history

Commits on Jul 30, 2024

  1. [CORE] add marlin inference kernel (#310)

    @ZX-ModelCloud
    ZX-ModelCloud authored Jul 30, 2024
    Configuration menu
    Copy the full SHA
    09ebcbb View commit details
    Browse the repository at this point in the history

  2. Update marlin.cuh (#313) 

    * Update marlin.cuh

* Update marlin_dtypes.cuh

* Update marlin_repack.cu
    @Qubitium
    Qubitium authored Jul 30, 2024
    Configuration menu
    Copy the full SHA
    b7b5395 View commit details
    Browse the repository at this point in the history

  3. [FIX] remove test_marlin_hf_cache_serialization() (#314)

    @ZX-ModelCloud
    ZX-ModelCloud authored Jul 30, 2024
    Configuration menu
    Copy the full SHA
    233548b View commit details
    Browse the repository at this point in the history
Loading