Skip to content
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.

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

Remove the AutoGPTQ loader #6641

Merged
merged 10 commits into from
Jan 8, 2025
Merged

Remove the AutoGPTQ loader #6641

merged 10 commits into from
Jan 8, 2025

Conversation

oobabooga
Copy link
Owner

@oobabooga oobabooga commented Jan 8, 2025

  • According to the AutoGPTQ README, the library has been discontinued.
  • GPTQ quants are uncommon for new model releases nowadays.
  • GPTQ is more sensitive to calibration than AWQ, as shown in the AWQ paper. Unfortunately, EXL2 inherits this issue because it's based on GPTQ.
  • ExLlamaV2 can load the same GPTQ models that AutoGPTQ could (or mostly).
  • Those who are interested can still install AutoGPTQ manually and load the model through Transformers.

@oobabooga oobabooga merged commit 7157257 into dev Jan 8, 2025
@oobabooga oobabooga deleted the remove-autogptq branch January 9, 2025 03:09
jfmherokiller pushed a commit to jfmherokiller/text-generation-webui that referenced this pull request Jan 15, 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