Cite
Notes
Only stored in your browser.
Attribution
FP4 All the Way: Fully Quantized Training of LLMs
arXiv 2025
Scaling FP8 training to trillion-token LLMs
arXiv 2024
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
arXiv 2020
from 3 papers
Daniel Soudry
Brian Chmiel
Maxim Fishman
Itay Hubara
Yair Hanani
Yury Nahshan