PulseAugur
中
实时 03:39:17
English(EN) METASTONE Launches TokenFleet to Schedule LLM Inference Across GPU Clusters and Data Centers

METASTONE推出TokenFleet以优化LLM推理调度

METASTONE推出了TokenFleet,这是一个旨在优化跨分布式GPU集群和数据中心的大型语言模型(LLM)推理调度的框架。该系统旨在通过降低延迟和提高吞吐量来改善性能。早期演示表明,P95首个令牌时间(time-to-first-token)和整体输出吞吐量均有显著提升。 AI

影响 优化LLM推理,可能降低AI应用的成本并改善响应时间。

排序理由 非前沿AI实验室公司的产品发布。

在 Pandaily 阅读 →

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

METASTONE推出TokenFleet以优化LLM推理调度

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
非前沿AI实验室公司的产品发布。
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
27 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. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    METASTONE 推出 TokenFleet,用于在 GPU 集群和数据中心调度 LLM 推理

    Compute operator METASTONE unveiled TokenFleet, a scheduling framework for LLM inference clusters. Its slides show P95 time-to-first-token down 32.4% and on-target output throughput up about 29.4%.