support GPTQ_FORMAT for "gptqmodel:exllamav2" backend#1434
Merged
Conversation
Signed-off-by: He, Xin3 <xin3.he@intel.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Adds support for GPTQ_FORMAT for the gptqmodel:exllamav2 backend, including a compatibility conversion for certain GPTQ qzero representations.
Changes:
- Introduced a
process_gptq_qzero()pass to adjustqzerosfor ExllamaV2 GPTQ layers. - Invoked qzero processing during
gptqmodelpost-init. - Expanded
gptqmodel:exllamav2backendpacking_formatto accept additional GPTQ formats.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 7 comments.
| File | Description |
|---|---|
| auto_round/inference/convert_model.py | Adds qzero conversion logic and hooks it into gptqmodel post-init. |
| auto_round/inference/backend.py | Updates exllamav2 backend packing_format to include GPTQ_FORMAT. |
This was referenced Feb 11, 2026
Kaihui-intel
approved these changes
Feb 11, 2026
Contributor
Kaihui-intel
left a comment
Kaihui-intel
left a comment
There was a problem hiding this comment.
Version check can also be added
chensuyue
pushed a commit
that referenced
this pull request
Feb 11, 2026
Signed-off-by: He, Xin3 <xin3.he@intel.com> (cherry picked from commit 8a3d793)
lvliang-intel
pushed a commit
that referenced
this pull request
Feb 27, 2026
Signed-off-by: He, Xin3 <xin3.he@intel.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
#1433
Type of Change
Related Issues
Fixes or relates to #1433
Checklist Before Submitting