PulseAugur
中
实时 17:18:41
English(EN) Huawei unveiled the OceanStor M900 at Huawei Connect 2026, adding a petabyte-scale key-value cache to its AI infrastructure for agents and long-context inferenc

华为推出 OceanStor M900 用于 AI 推理,配备 PB 级 KV 缓存 · 跟踪 2 个来源

华为推出了 OceanStor M900,这是一款专为超大规模推理设计的新型 AI 内存存储解决方案。该系统具有 PB 级键值 (KV) 缓存,旨在增强代理和长上下文推理等应用的 AI 基础设施。OceanStor M900 拥有 NPUs 和 SSD 之间的低延迟、高聚合带宽以及 KV 感知调度能力。 AI

影响 增强了超大规模推理和长上下文应用的 AI 基础设施。

排序理由 主要 AI 基础设施提供商的产品发布。 [lever_c_demoted from frontier_release: ic=2 ai=0.7]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

华为推出 OceanStor M900 用于 AI 推理,配备 PB 级 KV 缓存 · 跟踪 2 个来源

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
Significant
主要 AI 基础设施提供商的产品发布。 [lever_c_demoted from frontier_release: ic=2 ai=0.7]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
47 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 [2]

  1. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    华为OceanStor M900为AI SuperPoDs带来PB级共享KV缓存

    Huawei's OceanStor M900 AI memory storage targets hyperscale inference with Lingqu-pooled KV Cache up to 64 PB per cluster, ~60μs NPU-to-SSD latency, ~40 TB/s aggregate bandwidth, and KV-Aware scheduling claiming up to 24 DWPD.

  2. Mastodon — mastodon.social TIER_1 English(EN) · sipirtu ·

    华为在华为全联接2026大会上发布OceanStor M900,为其AI基础设施增加了PB级键值缓存,以支持智能体和长上下文推理

    Huawei unveiled the OceanStor M900 at Huawei Connect 2026, adding a petabyte-scale key-value cache to its AI infrastructure for agents and long-context inference. Source: DigiTimes Asia https://www. digitimes.com/news/a20260917VL 217/huawei-infrastructure-2026-data-performance.ht…