Skip to content

Conversation

wenhuach21
Copy link
Contributor

@wenhuach21 wenhuach21 commented Aug 15, 2025

autogptq add torch version restriction
int_sym code refine
zp sym packing optimization

@wenhuach21
Copy link
Contributor Author

transformers is ok, as we have kernels to backup autogptq kernels. For vllm, only 4btis and 8 bits if fine.

@wenhuach21 wenhuach21 closed this Aug 21, 2025
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.

1 participant