UniPIM: Hardware-Aligned Sparse LLM Inference for All-Bank Processing-in-Memory

Seulki Kim, Yewon Jang, Yunhyeong Jeon, Kyeonghyeon Ryu, and Daehoon Kim* IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2027

Keywords

Sparse LLM Inference, Processing-in-Memory.