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

Call for better/more documentation #921

Open
V0XNIHILI opened this issue Mar 25, 2024 · 0 comments
Open

Call for better/more documentation #921

V0XNIHILI opened this issue Mar 25, 2024 · 0 comments

Comments

@V0XNIHILI
Copy link

V0XNIHILI commented Mar 25, 2024

Dear Brevitas team,

I am really enjoying using your quantization framework. It gives great flexibility with really good performance. However, while I recently noticed that a lot of features around LLM quantization have been added, I find it harder and harder to keep up with all of these methods due to a lack of documentation. For now, my entire quantization stack is based on the TVMCon 2021 tutorial and the 'Anatomy of a Quantizer' tutorial. More recently, I have even been copying ideas from Hugging Face's wrapper around Brevitas as part of their Optimum workflow, which is very well documented: https://huggingface.co/docs/optimum/main/en/amd/brevitas/usage_guide

Therefore, I am wondering: would it be possible to reserve time in Brevitas development to write docstrings and extend the tutorials list with all the new, really cool things that are possible with Brevitas? I can also help with in areas of Brevitas that I used.

Best,
Douwe

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

No branches or pull requests

1 participant