KIVI

jy-yuan

[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

natural-language-processing

View on GitHub Website

438 Stars

58 Forks

7 Watchers

Python Language

mit License

100 SrcLog Score

Cost to Build

$780.6K

Market Value

$2.40M

How is this calculated?

Growth over time

7 data points · 2025-08-01 → 2026-11-01

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about KIVI

Question copied to clipboard

What is the jy-yuan/KIVI GitHub project? Description: "[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache". 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.

Add it to a GitHub README or profile — the card updates as the ranking changes:

How to clone KIVI

Clone via HTTPS

git clone https://github.com/jy-yuan/KIVI.git

Clone via SSH

[email protected]:jy-yuan/KIVI.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the KIVI issue tracker:

Open GitHub Issues

Similar to KIVI

lectures spaCy HanLP gensim stanford-tensorflow-tutorials nltk pattern awesome-nlp TextBlob CoreNLP allennlp mycroft-core practical-pytorch textract languagetool nlp_tasks MITIE Awesome-pytorch-list machine_learning_examples prose arXivTimes ltp libpostal sling DeepNLP-models-Pytorch sentencepiece DAT8 attention-is-all-you-need-pytorch kaggle-CrowdFlower iOS_ML