Skip to content

Fix multi-GPU GPTQ finalizer overlap#2808

Merged
Qubitium merged 7 commits intomainfrom
fix-issue-oom
Apr 23, 2026
Merged

Fix multi-GPU GPTQ finalizer overlap#2808
Qubitium merged 7 commits intomainfrom
fix-issue-oom

Conversation

@Qubitium
Copy link
Copy Markdown
Collaborator

@Qubitium Qubitium commented Apr 22, 2026

Fix: #2805

For multi-gpu gptq quants, we need to sync finalizers.

Comment thread gptqmodel/looper/awq_processor.py Fixed
@Qubitium Qubitium merged commit 94c04f4 into main Apr 23, 2026
6 checks passed
@Qubitium Qubitium deleted the fix-issue-oom branch April 23, 2026 04:18
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.

During the gptq quantization process, the gpu memory usage increases until the oom?

1 participant