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

[epage480]

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.

[Titus-von-Koeller]

@jiqing-feng (from Intel) Please provide the details to reproduce the benchmarks.

[jiqing-feng]

Fixed in #1554