Inference acceleration of large language models

Inference acceleration of large language models

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...

Full description

Bibliographic Details
Main Author: Zhang, Boyu
Other Authors: Mao Kezhi
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2024
Subjects:
Computer and Information Science
Large language model
Quantization
Approximate computation
Self-attention
Transformer
Online Access:https://hdl.handle.net/10356/181660

Internet

https://hdl.handle.net/10356/181660

Similar Items