Training an MoE LLM in MXFP4: How We Closed the Gap to BF16

Authors: Han Wang , Zhitao Wang , Natalia Frumkin , Xuanwu Yin , Alireza Khodamoradi , Dong Li , Emad Barsoum

View a PDF of the paper titled Training an MoE LLM in MXFP4: How We Closed the Gap to BF16, by Han Wang and 5 other authors

View PDF

HTML (experimental)

Abstract: Training large language models (LLMs) in sub-8-bit arithmetic promises substantial gains in memory bandwidth and compute throughput, yet FP4 formats introduce quantization error severe enough to destabilize optimization if left unaddressed. We present ALTO, an open-source training recipe for GPT-OSS-20B, a 20-billion-parameter mixture-of-experts (MoE) model, on the MLPerf Small MoE Training benchmark under the MXFP4 microscaling format. The recipe combines established techniques from Abecassis, Felix et al. [ arXiv:2509.25149 ] (hybrid 1D/2D block quantization, randomized Hadamard transforms, and stochastic rounding) with a simplified weight de-oscillation scheme adapted from TetraJet-v2 [ arXiv:2510.27527 ]. On C4 validation at global batch size 16, MXFP4 + RHT + SR + de-oscillation reaches a validation loss of 3.3350 at 16,128 steps, only 0.007 above the BF16 baseline (3.3283), closing roughly 50% of the gap left by MXFP4 without de-oscillation (3.3418). Measured by steps to reach the MLPerf quality target (validation loss 3.34), de-oscillation cuts the FP4 convergence overhead relative to BF16 from +20.0% to +5.0%. We also report negative end-to-end results from differential gradient estimation, outlier clipping, and macro-block scaling, despite each showing operator-level SNR gains. All experiments use simulated MXFP4 kernels on AMD MI300X hardware and wall-clock speed has not been optimized.

Subjects:

Artificial Intelligence (cs.AI)

Cite as:

arXiv:2610.32229 [cs.AI]

(or

arXiv:2610.32229v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.32229

Focus to learn more

arXiv-issued DOI via DataCite

Submission history

From: Han Wang [ view email ]

[v1]

Fri, 23 Oct 2026 06:40:21 UTC (280 KB)

[v2]

Mon, 26 Oct 2026 14:05:05 UTC (276 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Training an MoE LLM in MXFP4: How We Closed the Gap to BF16, by Han Wang and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

< prev

next >

new

recent

| 2026-10

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

export BibTeX citation

Loading...

BibTeX formatted citation

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer ( What is the Explorer? )

Connected Papers Toggle

Connected Papers ( What is Connected Papers? )

Litmaps Toggle

Litmaps ( What is Litmaps? )

scite.ai Toggle

scite Smart Citations ( What are Smart Citations? )

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv ( What is alphaXiv? )

Links to Code Toggle

CatalyzeX Code Finder for Papers ( What is CatalyzeX? )

DagsHub Toggle

DagsHub ( What is DagsHub? )

GotitPub Toggle

Gotit.pub ( What is GotitPub? )

Huggingface Toggle

Hugging Face ( What is Huggingface? )

ScienceCast Toggle

ScienceCast ( What is ScienceCast? )

Demos

Demos

Replicate Toggle

Replicate ( What is Replicate? )

Spaces Toggle

Hugging Face Spaces ( What is Spaces? )

Spaces Toggle

TXYZ.AI ( What is TXYZ.AI? )

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower ( What are Influence Flowers? )

Core recommender toggle

CORE Recommender ( What is CORE? )

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |

Disable MathJax ( What is MathJax? )