Skip to content

Does it support importing the AWQ model and then exporting it in the compressed-tensor format? #153

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
fengyang95 opened this issue Sep 8, 2024 · 2 comments
Open

Does it support importing the AWQ model and then exporting it in the compressed-tensor format? #153

fengyang95 opened this issue Sep 8, 2024 · 2 comments
Assignees
@brian-dellabetta
Labels
enhancement New feature or request

Comments

@fengyang95
Copy link

No description provided.

@mgoin mgoin added the enhancement New feature or request label Sep 21, 2024
@mgoin
Copy link
Member

mgoin commented Sep 21, 2024

It would be an interesting feature to write a converted from AutoAWQ format to compressed-tensors, this is not a priority but is possible.

@markurtz markurtz mentioned this issue Oct 18, 2024
Closed
@brian-dellabetta
Copy link
Contributor

Hi @fengyang95 , rather than integrating with AutoAWQ we are working to integrate its AWQ algorithm into our llm-compressor project, you can track this PR -- vllm-project/llm-compressor#1177.

@brian-dellabetta brian-dellabetta self-assigned this Mar 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@brian-dellabetta brian-dellabetta

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

[WIP] Autogptq checkpoint conversion support neuralmagic/compressed-tensors
3 participants
@mgoin @brian-dellabetta @fengyang95