RocketKV

[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

What is RocketKV?

[ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/nvlabsrocketkv.svg)](https://yunodb.com/tools/nvlabsrocketkv?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/nvlabsrocketkv?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/nvlabsrocketkv.svg" alt="Featured on YunoDB" height="20"></a>