随着各组织从简单的AI交互转向更长的对话、复杂的推理和自主智能体，其基础设施的需求也在发生变化。处理日益庞大的上下文对内存容量构成了重大压力，而保持加速器的数据供应则变得与原始计算能力同样重要。
As organizations move from straightforward AI interactions towards longer conversations, complex reasoning and autonomous agents, the demands on their infrastructure are changing. Processing increasingly large amounts of context places significant pressure on memory capacity, while keeping accelerators supplied with data becomes just as important as raw computing power.
一个特别的挑战是键值（KV）缓存，它存储在推理过程中生成的信息，以便模型可以重复使用先前的计算，而不是反复处理相同的上下文。随着上下文窗口的扩大和多轮交互变得更加苛刻，这些缓存大幅增长。GPU内存和系统内存提供快速访问，但价格昂贵且容量受限。传统存储提供更大的容量，但其较长的、由CPU中介的数据路径可能会引入延迟，导致宝贵的加速器资源在等待数据。华为认为，解决这一差距需要一种不同的存储方法。
One particular challenge is the key-value (KV) cache, which stores information generated during inference so models can reuse previous computations rather than repeatedly processing the same context. As context windows expand and multi-turn interactions become more demanding, these caches grow considerably. GPU memory and system memory provide fast access but are expensive and capacity constrained. Traditional storage offers greater capacity, yet its longer, CPU-mediated data paths can introduce latency that leaves valuable accelerator resources waiting for data. Huawei believes addressing this gap requires a different approach to storage.
在上海举行的2026华为全联接大会上，华为推出了OceanStor M900上下文内存存储，旨在支持超大规模数据中心及其升腾SuperPoD基础设施中的AI推理。该平台引入了华为所描述的专用上下文内存存储层，将KV缓存从加速器和系统内存扩展到共享的多级存储池中。
Bringing context memory closer to compute At HUAWEI CONNECT 2026 in Shanghai, Huawei introduced OceanStor M900 Context Memory Storage, designed to support AI inference across hyperscale datacenters and its Ascend SuperPoD infrastructure. The platform introduces what Huawei describes as a dedicated Context Memory Storage layer, extending KV cache beyond accelerator and system memory into a shared, multi-tier storage pool.
利用华为的UnifiedBus高速互连，OceanStor M900能够跨集群共享KV缓存资源，华为称其容量高达64PB，并且每个NPU可用的上下文大幅增加。其创新的ASU磁盘还集成了CPU、网络和存储控制器功能。结合原生的KV语义，这使得NPU能够单跳访问存储的缓存数据，避免了传统的协议转换和CPU转发。
Using Huawei's UnifiedBus high-speed interconnect, OceanStor M900 enables KV cache resources to be shared across a cluster, with Huawei claiming capacity of up to 64PB and substantially more context available per NPU. Its innovative ASU disk also integrates CPU, networking and storage controller functions. Combined with native KV semantics, this allows NPUs to access stored cache data in a single hop, avoiding conventional protocol conversion and CPU forwarding.
根据华为的说法，这种方法将访问延迟降低至60微秒，在典型的AI编码工作负载中，有可能将令牌吞吐量提高一倍，并将首个令牌生成时间缩短一半。
According to Huawei, this approach reduces access latency to 60 microseconds, potentially doubling token throughput and halving time to first token in typical AI coding workloads.
成本和耐用性也是该方案的一部分。华为的KV感知自适应存储技术根据缓存生命周期管理数据放置，据称耐用性高达每天24个驱动器写入，是传统固态硬盘的16倍。该公司认为，这可以降低随时间推移的更换和维护成本。
Cost and durability are also part of the proposition. Huawei's KV-aware adaptive storage technology manages data placement according to cache lifecycles, with claimed endurance of up to 24 drive writes per day, or 16 times that of conventional SSDs. The company argues this could reduce replacement and maintenance costs over time.
OceanStor M900更广泛的意义在于华为的AI基础设施方法。该公司没有将存储视为独立的支撑组件，而是将内存、网络和计算定位为推理性能中日益互联的要素。随着智能体AI工作负载的增长，基础设施保留、共享和检索上下文的效率可能会变得与其加速器处理它的速度一样重要。由华为赞助
The wider significance of OceanStor M900 lies in Huawei's approach to AI infrastructure. Rather than treating storage as a separate supporting component, the company is positioning memory, networking and compute as increasingly interconnected elements of inference performance. As agentic AI workloads grow, how efficiently infrastructure retains, shares and retrieves context may become as important as how quickly its accelerators can process it. Sponsored by Huawei