Cite
Notes
Only stored in your browser.
Attribution
Low-Rank Quantization-Aware Training for LLMs
arXiv 2024
The LLM Surgeon
arXiv 2023
FP8 Quantization: The Power of the Exponent
arXiv 2022
from 3 papers
Mart van Baalen
Tijmen Blankevoort
Andrey Kuzmin
Jorn Peters
Riccardo Del Chiaro
Tycho F. A. van der Ouderaa
Yelysei Bondarenko
Yuki M. Asano
Yuwei Ren