KIVI
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Test and improve the performance of large language models with a focus on numerical precision.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
KIVI has 431 stars on GitHub. It has been forked 59 times. KIVI is written mainly in Python. It has been in active development since 2024. KIVI is available under the MIT license. Its main topics are inference, large-language-models, llama, llm.
What is KIVI?
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Is KIVI open source?
KIVI is an open-source project. It is released under the MIT license.
Is KIVI free?
Yes. KIVI is free and open source — you can use, modify and self-host it.
What license does KIVI use?
KIVI is available under the MIT license.
What language is KIVI written in?
KIVI is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/jy-yuan-kivi.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.