An Empirical Study of Microscaling Formats for Low-Precision LLM Training

Yang, Hanmei; Deng, Summer; Nagpal, Amit; Naumov, Maxim; Janani, Mohammad; Liu, Tongping; Guan, Hui

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 10:00 PM ET on Thursday, July 16 until 12:00 AM ET on Friday 17 due to maintenance. We apologize for the inconvenience.

Citation Details

An Empirical Study of Microscaling Formats for Low-Precision LLM Training

Award ID(s):: 2449995 2435822 2338512 2312396 2220211 2224054

PAR ID:: 10628832

Author(s) / Creator(s):: Yang, Hanmei; Deng, Summer; Nagpal, Amit; Naumov, Maxim; Janani, Mohammad; Liu, Tongping; Guan, Hui

Publisher / Repository:: 2025 IEEE 32nd Symposium on Computer Arithmetic (ARITH)

Date Published:: 2025-04-17

Format(s):: Medium: X

Location:: 2025 IEEE 32nd Symposium on Computer Arithmetic (ARITH)

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
Accepted Manuscript
Conference Paper:
The DOI is not currently available.

More Like this