Inference acceleration of large language models

• 主要作者: Zhang, Boyu
• 其他作者: Mao Kezhi
• 格式: Thesis-Master by Coursework
• 語言: English
• 出版: Nanyang Technological University 2024
• 主題: Computer and Information Science; Large language model; Quantization; Approximate computation; Self-attention; Transformer
• 在線閱讀: https://hdl.handle.net/10356/181660

This dissertation delves into the challenges and bottlenecks faced by current large language models during inference from three core perspectives: data, model, and system. Through meticulous research, key factors impacting inference speed are identified, encompassing data processing efficiency, m...