作者位次 #4/8ACL 2026Poster· Natural Language Processing
From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion
Yanli Wang · Yanlin Wang · Bowen Zhang · Yiwei Zhang · Daya Guo · Jiachi Chen · Hongyu Zhang · Zibin Zheng
摘要
Code Large Language Models face critical Time-To-First-Token (TTFT) latency challenges when handling long code completion due to the quadratic complexity ( O(n^2) ) of attention mechanisms. While existing sparse attention methods attempt to address this issue, they suffer from three key limitatio...