Skip to content

Issues: neuralmagic/AutoFP8

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

10 Open 17 Closed
10 Open 17 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Qusetion] How can i see the net structure after i use autofp8
#46 opened Oct 17, 2024 by willnju
How to Quantize KV Cache for the deepseek-v2 Model
#44 opened Sep 12, 2024 by fengyang95
Quantize DeepSeek-Coder-V2-Instruct to W8A8(INT8)?
#42 opened Aug 21, 2024 by halexan
Differences in Dynamic Quantization Speedup for Varying SFT Tasks on Qwen2-72b-Instruct Models
#40 opened Aug 15, 2024 by IPostYellow
CUDA out of memory when quantizing llama3.1-405b on 80GiBx8 H100 instance
#36 opened Aug 7, 2024 by sfc-gh-zhwang
2
Support for Vision models
#34 opened Jul 19, 2024 by Syst3m1cAn0maly
Runtime Error:The weights trying to be saved contained shared tensors.
#31 opened Jul 15, 2024 by IEI-mjx
3
Integration with Hugging Face transformers library
#30 opened Jul 11, 2024 by SunMarc
3
error: RuntimeError: The weights trying to be saved contained shared tensors
#28 opened Jul 9, 2024 by AlphaINF
Bitblas supports FP8 Inference as well
#2 opened May 6, 2024 by LeiWang1999
3
ProTip! Find all open issues with in progress development work with linked:pr.