一作ACL 2026Poster· Natural Language Processing
E dge F ormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks
Yiming Yao · Jianwei Niu · Bin Dai · Tao Ren
摘要
Recent breakthroughs in Transformer-based large models, have driven widespread tasks, yet their reliance on centralized cloud deployment raises significant privacy risks due to sensitive data exposure. While edge-based collaborative inference offers a privacy-preserving alternative, existing meth...