Wire flash
Huawei launches OceanStor M900 AI memory storage based on LingQu at Connect 2026
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
At Huawei Connect 2026 on September 17, Huawei launched the OceanStor M900 AI memory storage solution built on LingQu. The product is designed for agent inference systems and long-sequence workloads, which require a multi-tier KV Cache architecture. Huawei proposed a multi-layer KV cache architecture and introduced the OceanStor M900 cluster, a PB-scale L3.5-layer KV cache based on LingQu UnifiedBus that supports 'one-hop direct connection.' The M900 employs mixed media combined with an optimized Retention algorithm, extending SSD read/write lifespan by 16 times to ensure high KV hit rates and long-term reliability at the underlying level.
Source report
Jin10 Data, September 17 — At today's Huawei Connect 2026, Huawei unveiled the OceanStor M900 AI memory storage solution, built on the LingQu platform.
Key Highlights
- Multi-Tier KV Cache Architecture: The solution addresses the requirements of agents and long-sequence workloads by introducing a multi-layer KV cache architecture for agent inference systems.
- OceanStor M900 Cluster: Huawei introduced the M900 cluster, a PB-scale L3.5-layer KV cache that leverages the LingQu UnifiedBus to support "one-hop direct connection."
- Mixed Media with Optimized Retention Algorithm: The M900 employs mixed media combined with an optimized Retention algorithm, extending SSD read/write lifespan by 16 times. This ensures high KV hit rates and long-term reliability at the underlying level.
Source
金十数据Eastern
Part of this Story
Huawei launches OceanStor M900 AI memory storage to tackle inference bottlenecks at Connect 2026