notesum.ai

Published at November 26

PIM-AI: A Novel Architecture for High-Efficiency LLM Inference

cs.AR
cs.AI
cs.DC
cs.ET

Released Date: November 26, 2024

Authors: Cristobal Ortega1, Yann Falevoz1, Renaud Ayrignac1

Aff.: 1UPMEM

Arxiv: http://arxiv.org/abs/2411.17309v1