local-turboquant

Unofficial Python library implementing TurboQuant (Q_mse and Q_prod) KV cache compression for HuggingFace Transformers. One-line activate() API plus a CLI. Tested on Llama 3.1 and Qwen 2.5.

modal

View on GitHub

2 Stars

0 Forks

1 Watchers

Python Language

32.1 SrcLog Score

Cost to Build

$6.8K

Market Value

$3.9K

How is this calculated?

Growth over time

6 data points · 2026-04-08 → 2026-08-28

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about local-turboquant

Question copied to clipboard

What is the 0x3ddie/local-turboquant GitHub project? Description: "Unofficial Python library implementing TurboQuant (Q_mse and Q_prod) KV cache compression for HuggingFace Transformers. One-line activate() API plus a CLI. Tested on Llama 3.1 and Qwen 2.5.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone local-turboquant

Clone via HTTPS

git clone https://github.com/0x3ddie/local-turboquant.git

Clone via SSH

[email protected]:0x3ddie/local-turboquant.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the local-turboquant issue tracker:

Open GitHub Issues

Similar to local-turboquant

sweetalert ng-bootstrap fancybox bootstrap-modal react-modal PopupDialog zuck.js intense-images Presentr jquery-modal baguetteBox.js react-portal lightbox react-native-modal AlertifyJS Micromodal react-native-modal-datetime-picker react-native-loading-spinner-overlay tingle lity ngx-modialog react-overlays react-native-modal-dropdown MediumLightbox rmodal.js heyui simplelightbox rodal sweet-modal-vue expodal