NDPool: Correctness-Preserving Shared Execution for Efficient LLM Inference on CXL-NDP Systems

Yeji Jung, Hwanjun Lee, Sungju Kim, Seulki Kim, Yunhyeong Jeon, and Daehoon Kim*. IEEE Computer Architecture Letters (CAL), 2026

Abstract

Keywords

NDP, CXL, LLM.