Cite
Notes
Only stored in your browser.
Attribution
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
arXiv 2024
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
from 2 papers
James Hensman
Saleh Ashkboos
Torsten Hoefler
Amirkeivan Mohtashami
Bo Li
Dan Alistarh
Marcelo Gennari do Nascimento
Martin Jaggi
Pashmina Cameron