Skip to content
AI News HubLIVE
Original source2 min read

Advancing Quantization for R&R Models with Microscaling Formats

Summary

An arXiv paper evaluates MXFP8 and 6-bit MXFP6 microscaling formats for industrial-scale recommendation and ranking (R&R) inference on AMD MI350X, reporting significant GEMM kernel speedups over FP16 and end-to-end throughput gains from selective MXFP6 under a strict NE parity threshold.

SourcearXiv AIAuthor: Yavuz Yetim, Bor-Yiing Su, Zhe Wang, Arthur Liu, Pranav Sharma, Ying Wang, Randy Shuai, Luke Pfister, Ruichao Xiao, Bill Zhao, Zihao Liu, Liyuan Li, Jiangyuan Li, Gaoxiang Liu, Nathan Yan, Geonhwa Jeong, Jatin Chhugani, Elias Ellison, Uladzimir Pashkevich
Advancing Quantization for R&R Models with Microscaling Formats
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:Advancing Quantization for R&R Models with Microscaling Formats

View a PDF of the paper titled Advancing Quantization for R&R Models with Microscaling Formats, by Yavuz Yetim and 18 other authors

View PDF HTML (experimental)

Abstract:Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quantization-induced accuracy drops of 1% or more, production-grade R&R models enforce a stringent launch bar: model quality must remain within a 0.01% Normalized Entropy (NE) margin relative to the baseline, which commonly uses FP16 or FP32. This tight constraint has historically hindered the adoption of aggressive quantization in this domain. In this paper, we present an empirical evaluation of both MXFP8 and the 6-bit MXFP6 format for industrial-scale R&R inference on the AMD MI350X architecture.

To the best of our knowledge, this is the first paper, across R&R and LLM domains, that reports significant speedups from native MXFP6 GEMMs, which quantize both weights and activations and compute directly on 6-bit elements, without sacrificing model quality. We demonstrate that we can selectively apply this 6-bit format to maximize overall QPS gain without breaching the strict NE parity threshold. We further show that MXFP8 is a viable alternative to row-wise FP8: the two formats have nearly the same accuracy on our models, so the faster kernel can be chosen for each GEMM shape. On two production ads ranking models, our implementation shows measured GEMM kernel speedups over FP16 of 1.33--1.55x for MXFP8 and 1.73--1.99x for MXFP6 across all supported linear layers, and up to 2.90x for MXFP6 on individual layers, alongside end-to-end (E2E) inference throughput gains from selective MXFP6 of 1.5--5.3% for Model A and 7.6--14.3% for Model B over their FP8 configurations.

Subjects:

Artificial Intelligence (cs.AI)

ACM classes: I.2.6; G.1.0; C.4

Cite as: arXiv:2611.17501 [cs.AI]

(or arXiv:2611.17501v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.17501

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bor-Yiing Su [view email] [v1] Thu, 12 Nov 2026 20:46:31 UTC (57 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Advancing Quantization for R&R Models with Microscaling Formats, by Yavuz Yetim and 18 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • First to report significant speedups from native MXFP6 GEMMs in both R&R and LLM domains without model quality loss.
  • MXFP8 is a viable alternative to row-wise FP8 with nearly identical accuracy, allowing selection of the faster kernel per GEMM shape.
  • GEMM kernel speedups over FP16 reach 1.73–1.99x for MXFP6 across linear layers, up to 2.90x on individual layers.
  • Selective MXFP6 yields end-to-end inference throughput gains of 1.5–5.3% for Model A and 7.6–14.3% for Model B over FP8.

Highlights and analysis are generated automatically and may contain errors. Check the original source.