Skip to content

Issues: mit-han-lab/smoothquant

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

64 Open 25 Closed
64 Open 25 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

how to visual outier of activation
#97 opened Nov 3, 2024 by harleyszhang
The upper and lower bounds seems to not 8 bits in some cases
#96 opened Oct 30, 2024 by zhangyu68
Why only 4 layers?
#95 opened Sep 7, 2024 by VincentXWD
Support for Qwen2
#94 opened Jul 31, 2024 by JiaXinLI98
How to quantize the out_proj and fc2 module in OPT model family
#93 opened Jul 30, 2024 by yanchenmochen
How to quantize llama3?
#92 opened Jul 22, 2024 by jpyo0803
export_int8_model.py size issue
#91 opened Jul 11, 2024 by ljhyeok123
1
quantify other models,
#90 opened Jul 9, 2024 by AlexMa0
best Alpha value for Qwen 1.5 72B
#89 opened Jun 26, 2024 by Riskin1999
how to draw this result directly? is there any script?
#88 opened Jun 5, 2024 by foreverpiano
1
Huggingface_Hub Issue
#87 opened May 23, 2024 by faize5
2
Can SmoothQuant be used on ViT models?
#86 opened Apr 24, 2024 by n9s8a
Whether it can be supported stable diffusion
#85 opened Apr 11, 2024 by songh11
Inquiry about Int8 BMM overflow
#84 opened Apr 9, 2024 by luzai
Error when running smoothquant_opt_real_int8_demo.ipynb
#83 opened Apr 2, 2024 by kaijun924
how to use model.generate with smoothquant models
#82 opened Mar 31, 2024 by Hao-YunDeng
which version of transformer and datasets package do we need for this repo?
#81 opened Mar 28, 2024 by ghost
2
adjust activations
#80 opened Mar 28, 2024 by muzi0111
Question: why not need explicit scaling for activation X
#79 opened Mar 18, 2024 by ghost
2
Weight migration for Llama?
#77 opened Mar 14, 2024 by atyshka
Question about code
#76 opened Mar 6, 2024 by Lucky-Lance
How Can I Peft the Smoothquanted LLM?
#75 opened Mar 5, 2024 by LameloBally
1
Can I reproduce SmoothQuant on CPU only since I see that torch-int8 requires a GPU, and I am only interested in inference on the CPU?
#73 opened Feb 7, 2024 by WCSY-YG
set quantize_output True the acc drop to 0
#72 opened Jan 15, 2024 by lonleyodd
ask for a function in linear.py for smoothquant in llama @Anizpz
#71 opened Jan 2, 2024 by msz12345
ProTip! Find all open issues with in progress development work with linked:pr.