Skip to content
Hot storiesContinuously updated

中科曙光提出AI数据工厂存储范式与ParaCache方案

1 reports1 reporting sourcesUpdated 6 hours ago

Start here

AI overview

面对Agent场景下的长上下文与多轮交互需求,中科曙光提出“AI数据工厂”存储新范式,将存储从传统被动的数据容器转变为主动参与Token生成的生产要素。同时,中科曙光推出了原生支持KV Cache语义的ParaCache方案。实测数据显示,在将KV Cache卸载至L4分布式存储后,Token吞吐量可提升15到25倍,且单TB成本仅约为内存的四十分之一。

AI-generated from reports · Updated 6 hours ago

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. IT168 服务器存储 · AI与算力
    中科曙光:Token时代,存储为何必须“重造”自己?

    面对 Agent 场景下的长上下文与多轮交互需求,中科曙光提出“AI数据工厂”存储范式,将存储从被动数据容器转变为主动参与 Token 生成的生产要素。其 ParaCache 方案原生支持 KV Cache 语义,实测将 KV Cache 卸载至 L4 分布式存储后 Token 吞吐提升 15 到 25 倍,且单 TB 成本仅约为内存的 1/40。

Story heat trend

Current heat 9·Comparable peak 10(Nov 5 12:00)·Comparable change, last 24 hours–

02.557.510Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.