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: v0.9.5
Choose a base ref
...
head repository: ModelCloud/GPTQModel
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.9.6
Choose a head ref
  • 5 commits
  • 21 files changed
  • 4 contributors

Commits on Jul 6, 2024

  1. [FIX] [MISC] Update test (#177)

    * update assert usage
    
    * assert less than 0.0068
    CSY-ModelCloud authored Jul 6, 2024
    Configuration menu
    Copy the full SHA
    399691e View commit details
    Browse the repository at this point in the history

Commits on Jul 7, 2024

  1. cleanup triton (#178)

    Qubitium authored Jul 7, 2024
    Configuration menu
    Copy the full SHA
    c3f11a0 View commit details
    Browse the repository at this point in the history
  2. [CORE] Add AutoRound as Quantizer option (#166)

    * add quant_method auto_round
    
    * if use auto_round, can't use torch.inference_mode()
    
    * pass dataloder
    
    * fix collate_batch
    
    * cleanup code
    
    * pack model to auto_round
    
    * cleanup config.py
    
    * add test case
    
    * format code
    
    * use our tritonv2 qlinear
    
    * add type hint
    
    * self.qlinear_kernel = qlayer
    
    * auto_round also need convert v2 to v1
    
    * add ppl test
    
    * add auto_round ppl test
    
    * mod method check
    
    * revert desc_act
    
    * add auto-round requirement
    
    * auto-round must be 0.2
    
    ---------
    
    Co-authored-by: LRL-ModelCloud <[email protected]>
    LRL-ModelCloud and LRL2-ModelCloud authored Jul 7, 2024
    Configuration menu
    Copy the full SHA
    c945b35 View commit details
    Browse the repository at this point in the history

Commits on Jul 8, 2024

  1. cleanup (#180)

    Co-authored-by: LRL-ModelCloud <[email protected]>
    LRL-ModelCloud and LRL2-ModelCloud authored Jul 8, 2024
    Configuration menu
    Copy the full SHA
    d866208 View commit details
    Browse the repository at this point in the history
  2. doc 0.9.6 (#181)

    Qubitium authored Jul 8, 2024
    Configuration menu
    Copy the full SHA
    4fade4c View commit details
    Browse the repository at this point in the history
Loading