Skip to content

quick fix: gptqmodel no longer includes gptqmodel_marlin_kernels#1671

Open
xin3he wants to merge 1 commit intomainfrom
xin3he-patch-1
Open

quick fix: gptqmodel no longer includes gptqmodel_marlin_kernels#1671
xin3he wants to merge 1 commit intomainfrom
xin3he-patch-1

Conversation

@xin3he
Copy link
Copy Markdown
Contributor

@xin3he xin3he commented Apr 9, 2026

Description

Please briefly describe your main changes, the motivation.

Type of Change

  • Bug fix
  • New feature
  • Documentation update
  • Performance improvement
  • Code refactoring
  • Other (please specify):

Related Issues

Fixes or relates to #

Checklist Before Submitting

  • My code has been tested locally.
  • Documentation has been updated as needed.
  • New or updated tests are included where applicable.

@xin3he xin3he requested review from Copilot and wenhuach21 April 9, 2026 13:31
@xin3he
Copy link
Copy Markdown
Contributor Author

xin3he commented Apr 9, 2026

/azp run Unit-Test-CUDA-AutoRound

@azure-pipelines
Copy link
Copy Markdown

Azure Pipelines successfully started running 1 pipeline(s).

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the Marlin kernel import path used by get_marlin_layer() to handle newer gptqmodel releases where gptqmodel_marlin_kernels is no longer shipped as a top-level module.

Changes:

  • Add a fallback import to gptqmodel.utils.marlin when import gptqmodel_marlin_kernels fails.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants