From 2: 4 to 8: 16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction.
Egor Maximov, Yulia Kuzkina, Egor Shvetsov, Azamat Kanametov, Alexander Prutko, Maxim Zhelnin, Aleksei Goncharov
Browse the full ACL paper archive.
Egor Maximov, Yulia Kuzkina, Egor Shvetsov, Azamat Kanametov, Alexander Prutko, Maxim Zhelnin, Aleksei Goncharov
Browse the full ACL paper archive.