Skip to content

Issues: SqueezeAILab/SqueezeLLM

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

15 Open 12 Closed
15 Open 12 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

When I use SqueezeLLM to quantize the LLaMA2-13B model and test it, the speed is extremely slow.
#71 opened Jul 3, 2024 by zhangfzR
Can you update the version that can quant OPT family?
#70 opened Jun 26, 2024 by Chen-1031
how can I get the models of 0.45% sparsity by myself?
#69 opened Jun 17, 2024 by LiMa-cas
Why do LLaMA-2-7B have s0 quantized models, but no s5 and s45 sparsity quantized models?
#68 opened May 26, 2024 by Evane5cence
Further speeding up the quantization process
#67 opened May 5, 2024 by SyphonArch
Installation instructions did not lead to the local transformers version being selected, giving errors
#66 opened Apr 9, 2024 by RDouglasSharp
Support JAIS models
#65 opened Mar 24, 2024 by 7ossam81
Dense-only quantization bit precision
#63 opened Mar 5, 2024 by akarkim
D+S packing in vLLM seems buggy
#62 opened Feb 27, 2024 by MingLin-home
sample_weight is negative when running kmeans clustering
#61 opened Feb 23, 2024 by MingLin-home
A question about LLaMA-2-7B and Mistral models only provide Dense-only (0%) quantized models
#56 opened Feb 4, 2024 by WeiMa01
On A100 card, speed-up effect does not show up.
#51 opened Nov 30, 2023 by leocnj
2
Future plan for this project
#45 opened Nov 1, 2023 by tjtanaa
Vicuna-1.5?
#44 opened Oct 29, 2023 by mlinmg
Minor bug for --include_sparse
#39 opened Aug 11, 2023 by vuiseng9
ProTip! no:milestone will show everything without a milestone.