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

Link to code for reproducing table found in Multi-backend support (non-CUDA backends) documentation? #1456

Open
epage480 opened this issue Dec 17, 2024 · 0 comments
Open

Link to code for reproducing table found in Multi-backend support (non-CUDA backends) documentation? #1456

epage480 opened this issue Dec 17, 2024 · 0 comments

Comments

@epage480
Copy link

epage480 commented Dec 17, 2024 •
edited
Loading

Feature request

It is unclear how the CPU inference and fine-tuning benchmarks were produced. It would be nice to have links to the example code used to produce them. https://huggingface.co/docs/bitsandbytes/main/en/non_cuda_backends

Motivation

I've struggled to reproduce these metrics, any resources on how they were made would be helpful.

Your contribution

If I could reproduce it myself I would already have a PR but I'm willing to help with some guidance.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@epage480