PulseAugur
中
实时 06:57:12

New 6-bit and 8-bit formats boost R&R model inference speed without quality loss

研究人员开发了新的微缩格式MXFP8和MXFP6,以提高数字广告中使用的推荐和排序(R&R)模型的效率。这些模型对精度损失高度敏感,要求质量保持在与FP16或FP32相比0.01%的误差范围内。新格式能够显著提高推理吞吐量的速度,其中MXFP6相比FP16的速度提升了1.73倍至1.99倍,在单个层上最高可达2.90倍,同时保持了模型质量。 AI

影响 能够在大规模应用(如数字广告)中更快、更高效地部署关键的推荐和排序模型。

排序理由 该集群包含一篇详细介绍AI模型优化新技术的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

New 6-bit and 8-bit formats boost R&R model inference speed without quality loss

本文如何被排名

Signal score
37 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍AI模型优化新技术的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · 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

    arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&amp;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 q…