Skip to content

Conversation

@xin3he
Copy link
Contributor

@xin3he xin3he commented Feb 12, 2026

Description

Rename process_gptq_qzero to convert_gptq_v1_to_v2 and update logic for compatibility with gptqmodel:exllamav2 backend

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.

…or compatibility with gptqmodel:exllamav2 backend

Signed-off-by: He, Xin3 <xin3.he@intel.com>
Copy link
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

This PR refactors the GPTQ format conversion logic to improve compatibility with the gptqmodel:exllamav2 backend. The function is renamed to better reflect its purpose, and conversion is now conditionally applied based on the packing format configuration.

Changes:

  • Renamed process_gptq_qzero to convert_gptq_v1_to_v2_format for clarity
  • Added conditional logic to only convert when packing format is "auto_round:gptq" (v1)
  • Updated inline comments to clarify v1 vs v2 format distinction

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@chensuyue chensuyue added this to the 0.10.0 milestone Feb 12, 2026
@chensuyue chensuyue merged commit 86231c4 into main Feb 12, 2026
29 checks passed
@chensuyue chensuyue deleted the xinhe/2-12 branch February 12, 2026 05:57
chensuyue added a commit that referenced this pull request Feb 12, 2026
Signed-off-by: He, Xin3 <xin3.he@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
(cherry picked from commit 86231c4)
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.

4 participants