Skip to content
AI情报Sep 18, 2026AI情报
文章

Huawei unveiled the OceanStor M900 AI memory storage…

…targeting hyperscale inference with a Lingqu-pooled KV cache up to 64 PB per cluster, ~60μs NPU-to-SSD latency, and ~40 TB/s aggregate bandwidth. The system aims to ease KV cache bottlenecks in large-scale AI serving.

AI 生成：摘要由 AI 根据所链接的来源撰写。 我们如何使用 AI

AI 生成来源: Pandaily
01

来源简报

Huawei unveiled the OceanStor M900 AI memory storage, targeting hyperscale inference with a Lingqu-pooled KV cache up to 64 PB per cluster, ~60μs NPU-to-SSD latency, and ~40 TB/s aggregate bandwidth. The system aims to ease KV cache bottlenecks in large-scale AI serving.

02