MatKV: Trading Compute for Flash Storage in LLM Inference

Kunwoo Shin, Jay H. Park, Moonwook Oh, Yohan Jo, Jaeyoung Do, Sang-Won Lee. MatKV: Trading Compute for Flash Storage in LLM Inference. In 42nd IEEE International Conference on Data Engineering, ICDE 2026, Montreal, QC, Canada, May 4-8, 2026. pages 877-890, IEEE, 2026. [doi]

Abstract

Abstract is missing.