Skip to content

Issues: IST-DASLab/gptq

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

20 Open 28 Closed
20 Open 28 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

Test on CNN model containing group conv by GPTQ method
#56 opened May 23, 2024 by xd1073321804
Reconstruct Quantized Model Layer in torch.
#55 opened May 19, 2024 by puja93
GPTQ on BERT based
#53 opened Feb 13, 2024 by zhanyil2
AssertionError
#52 opened Jan 30, 2024 by GuoYi0
Regarding the method for computing the Hessian matrix.
#51 opened Dec 29, 2023 by baiSongL
1
GPTQ pseudo-quantization saved weights (pt format) How load Re-evaluation
#50 opened Dec 21, 2023 by CXiaorong
GPTQ转化的INT8模型，如何运行呢？请大佬指教
#49 opened Dec 13, 2023 by xxm1668
Compatibility of Quant3Linear and 4-bit quantization
#48 opened Dec 10, 2023 by mynotwo
act-order on inference
#47 opened Dec 3, 2023 by frankxyy
running speed slow on NVIDIA vGPU
#45 opened Nov 11, 2023 by foricee
Use modified Cholesky decomposition instead of regularized Cholesky
#41 opened Aug 7, 2023 by jiahao
Why is the wikitext-2 ppl calculated in the code lower than the ppl by lm-evaluation-harness?
#40 opened Aug 6, 2023 by Chocolife-96
LAMBADA evaluation accuracy
#39 opened Aug 5, 2023 by kayhanbehdin
How should I verify the speedup effect of the algorithm?
#38 opened Jul 20, 2023 by moonlightian
How to run the quantized model for perditions on my prompts?
#37 opened Jul 18, 2023 by tarunmcom
How can we use this lib to quantize Falcon7b / 40b models?
#36 opened Jul 17, 2023 by tarunmcom
How to adopt GPTQ on Conv2d with groups attribute?
#35 opened Jul 14, 2023 by TMYuan
1
PPL results on wikitext/ptb/c4 are worse than the official result
#34 opened Jul 6, 2023 by xingyueye
2
quant_cuda_kernel.cu(212): error: identifier "__hfma2" is undefined
#23 opened May 11, 2023 by HueCheng1021
1
Application to T5 / UL2 family
#8 opened Mar 8, 2023 by iiLaurens
7
ProTip! no:milestone will show everything without a milestone.