ResearchTrend.AI
eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization

eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization

Aditya Agrawal
Matthew Hedlund
Blake A. Hechtman
    MQ
ArXivPDFHTML

Papers citing "eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization"

2 / 2 papers shown
Title
Tilus: A Virtual Machine for Arbitrary Low-Precision GPGPU Computation in LLM Serving
Tilus: A Virtual Machine for Arbitrary Low-Precision GPGPU Computation in LLM Serving
Yaoyao Ding
Bohan Hou
X. Zhang
Allan Lin
Tianqi Chen
Cody Yu Hao
Yida Wang
Gennady Pekhimenko
41
0
0
17 Apr 2025
Scaling laws for post-training quantized large language models
Scaling laws for post-training quantized large language models
Zifei Xu
Alexander Lan
W. Yazar
T. Webb
Sayeh Sharify
Xin Eric Wang
MQ
26
0
0
15 Oct 2024