PulseAugur
实时 21:45:09
English(EN) Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

Gleam框架赋能高效跨设备GPU共享以进行AI推理

研究人员开发了Gleam,一个旨在实现局域网内跨设备高效GPU共享以进行AI推理的框架。Gleam通过实现自动模型权重缓存以减少带宽、异步执行以缓解频繁API调用的延迟,以及一个动态运行时任务调度器来根据网络状况和GPU争用情况优化API远程调用对,从而解决网络瓶颈。该系统还确保了跨分布式执行的CUDA上下文一致性。实验表明,Gleam在API远程调用效率和整体系统吞吐量方面显著优于现有方法,适用于各种AI工作负载和NVIDIA GPU。 AI

影响 通过利用分布式GPU,可能实现更广泛、更高效的消费级硬件AI推理。

排序理由 该项目是一篇研究论文,详细介绍了一个新的GPU共享框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

Gleam框架赋能高效跨设备GPU共享以进行AI推理

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目是一篇研究论文,详细介绍了一个新的GPU共享框架。[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
infra, product
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
52 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Zhihao Xu, Hao Zhong, Zeting Zhou, Yuhang Xu, Haoyu Tong, Wei Wang, Jinshan Chen, Keqiang He, Chong Zhu, Shengzhong Liu, Fan Wu, Guihai Chen ·

    Gleam:跨设备局域网GPU共享的自适应网络高效CUDA API远程处理

    arXiv:2607.23115v1 Announce Type: cross Abstract: This paper aims to enable computation- and communication-efficient GPU sharing across devices within local area networks (LANs), facilitating ubiquitous AI inference on heterogeneous personal devices. We achieve distributed task o…