English(EN) Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts

新框架优化万亿参数MoE模型以提高效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

研究人员开发了一个新的框架，用于优化混合专家（MoE）语言模型，该模型可以扩展到万亿参数。该框架解决了部署如此大型模型所带来的显著内存和带宽限制。通过采用硬件原生稀疏量化技术和定制分组稀疏GEMM内核，该系统在NVIDIA B200 GPU上实现了准确性、服务吞吐量和延迟降低方面的显著改进。 AI

影响这项研究可能能够更有效地部署超大型语言模型，从而降低推理成本并提高可访问性。

排序理由该项目是一篇学术论文，详细介绍了一个用于优化AI模型的新技术框架。[lever_c_demoted from research: ic=1 ai=1.0]

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

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇学术论文，详细介绍了一个用于优化AI模型的新技术框架。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Kwanhee Lee, Namhoon Lee, Dan Alistarh · 2026-10-05 04:00

面向万亿规模专家混合模型的硬件原生联合稀疏-量化

arXiv:2610.02241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures allow frontier language models to scale to trillions of parameters, but their deployment is constrained by massive memory footprints and memory-bandwidth limitations. Although modern accelera…