jjiantong/Awesome-KV-Cache-Optimization

This is a curated collection of research papers and resources focused on making large language models (LLMs) run more efficiently without changing their core design or needing retraining. It categorizes and explains various techniques for optimizing how LLMs store and retrieve information during use, aiming to improve speed and reduce resource consumption. AI/ML system engineers, researchers, and infrastructure managers who deploy and maintain LLMs would find this useful.

310 stars.