作者位次 #2/7ACL 2026Poster· ACL Industry Track
From 2:4 to 8:16 sparsity patterns in LLM s for Outliers and Weights with Variance Correction
Egor Maximov · Yulia Kuzkina · Egor Shvetsov · Azamat Kanametov · Aleksandr Prutko · Maxim Zhelnin · Aleksei Goncharov
摘要
As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity methods, such as N:M sparsification, often fall short due to limited flexibility a...