Cite
Notes
Only stored in your browser.
Attribution
ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs
arXiv 2022
HAWQV3: Dyadic Neural Network Quantization
arXiv 2020
from 2 papers
Amir Gholami
Chengquan Jiang
Eric Tan
Jiali Yu
Kurt Keutzer
Michael W. Mahoney
Qijing Huang
Shang Zhang
Xiaoying Jia
Xin Liu