Huawei OceanStor M900 brings PB-Class shared KV cache to AI SuperPoDs
Huawei OceanStor M900 Brings PB-Class Shared KV Cache to AI SuperPoDs
This matters to AI practitioners as it provides a high-performance, large-scale shared memory solution for large language model inference, potentially improving efficiency and reducing latency compared to traditional storage methods.
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.
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to Chinese AI companies expanding and localizing across Southeast Asia. Key entities and technical topics under continuous tracking include OceanStor M900, Huawei, AI storage, supercomputing clusters.
Primary source verification: published directly by pandaily with first-party authority.
