MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zheming, Guo, Qi, Hu, Yunqing, Zhao, Chang, Zhang, Chang, Zhao, Jian, Ji, Wen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!