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.

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

exllama vs autogptq #39

Open
surcyf123 opened this issue Sep 11, 2023 · 2 comments
Open

exllama vs autogptq #39

surcyf123 opened this issue Sep 11, 2023 · 2 comments
Assignees
@gee842
Labels
high priority

Comments

@surcyf123
Copy link
Owner

surcyf123 commented Sep 11, 2023 •
edited
Loading

Need to switch to exllama, everything I'm reading about is how exllama is better. At least for production we will need to switch. Speed is everything at the inference volume we expect. Note to try VLLM too
@surcyf123
Copy link
Owner Author

https://oobabooga.github.io/blog/posts/perplexities/

"(updated) bitsandbytes load_in_4bit vs GPTQ + desc_act: load_in_4bit wins in 3 out of 4 tests"

@surcyf123
Copy link
Owner Author

oh thats 2 months old

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@gee842 gee842

Labels
high priority
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@gee842 @surcyf123