Home Projects KVCache-Factory
KVCache-Factory
Python

KVCache-Factory

Unified KV Cache Compression Methods for Auto-Regressive Models

by Zefan-Cai · GitHub
Stars
Forks
Trending
License
Created
Last commit
Category
Language
kv-cachekv-cache-compressionllmMITPython
View on GitHub
In plain words

Explore different methods to compress and manage data for AI models in a single interface.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
KVCache-Factory — GitHub preview card
📈 Star history
1.38k1.35k
2026-07-202026-08-31
📈 Track KVCache-Factory

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Unified KV Cache Compression Methods for Auto-Regressive Models

KVCache-Factory has 1.4k stars on GitHub. It has been forked 179 times. KVCache-Factory is written mainly in Python. It has been in active development since 2024. KVCache-Factory is available under the MIT license. Its main topics are kv-cache, kv-cache-compression, llm.

Frequently asked questions

What is KVCache-Factory?

Unified KV Cache Compression Methods for Auto-Regressive Models

Is KVCache-Factory open source?

KVCache-Factory is an open-source project. It is released under the MIT license.

Is KVCache-Factory free?

Yes. KVCache-Factory is free and open source — you can use, modify and self-host it.

What license does KVCache-Factory use?

KVCache-Factory is available under the MIT license.

What language is KVCache-Factory written in?

KVCache-Factory is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — KVCache-Factory

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=zefan-cai-kvcache-factory)](https://olud.ai/project/zefan-cai-kvcache-factory.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.