SMOOTH: Hardware-Assisted Fine-Grained On-Chip Memory Management for Efficient On-Device LLM Inference.
Seulki Kim, Bokyeong Kim, Kyeonghyeon Ryu, Yeji Jung, Hwanjun Lee, Sungju Kim, Yunhyeong Jeon, Daehoon Kim
Browse the full ISCA paper archive.
Seulki Kim, Bokyeong Kim, Kyeonghyeon Ryu, Yeji Jung, Hwanjun Lee, Sungju Kim, Yunhyeong Jeon, Daehoon Kim
Browse the full ISCA paper archive.