作者位次 #3/6ACL 2026Poster· Natural Language Processing
Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models
Cuong Pham · Anh Dung Hoang · Cuong C. Nguyen · Trung Le · Gustavo Carneiro · Thanh-Toan Do
摘要
Large language models (LLMs) have advanced natural language processing, but their massive parameter counts create computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged as a promising approach to mitigate these challenges. While existing PTQ methods ca...