TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI 文章

ArXiv CS.AI2026-06-01NEWSen作者: Hyunwoo Oh, Hanning Chen, Sanggeon Yun, Yang Ni, Suyeon Jang, Behnam Khaleghi, Fei Wen, Mohsen Imani
查看原文 →
关系图谱

TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI · 相关技术

相关技术

token pruningDALORADTSpMMDDMMFPGAtransformer NLPGNNCNNsViTs