ULSeq-TA: Ultra-Long Sequence Attention Fusion Transformer Accelerator Supporting Grouped Sparse Softmax and Dual-Path Sparse LayerNorm
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS（2024）
关键词
Transformers,Task analysis,System-on-chip,Decoding,Sparse matrices,Hardware,Transformer cores,Long sequence,software-hardware co-design,sparse LayerNorm,sparse Softmax,transformer accelerator
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要