技术简介

AI处理器执行支撑AI工作负载所需的矩阵乘法等复杂计算。6
AI processors handle the complex computations, such as matrix multiplications, required to power AI workloads.
复杂AI需求需要在CPU之外增加硬件，通过并行计算提升性能。6
Complex AI needs require additional hardware beyond the CPU to unlock more performance through a parallel computing approach.

已有应用

OpenAI在Abilene使用含超过10万枚英伟达Blackwell GPU的OCI超级集群训练和服务GPT-6 Astra。1
In Abilene, OpenAI has trained and served GPT-6 Astra on an OCI Supercluster with more than 100,000 NVIDIA Blackwell GPUs.
Azure的模型开发者现可使用AMD算力训练和服务大规模AI模型。3
Frontier model builders can now leverage AMD-powered infrastructure to train and serve large-scale AI models, while enterprise customers can deploy and scale production AI workloads through Azure Foundry Managed Compute.
Anthropic和亚马逊已建成Project Rainier，Anthropic正在使用超过一百万枚Trainium2芯片训练和服务Claude。5
Together we launched Project Rainier, one of the largest compute clusters in the world, and we currently use over one million Trainium2 chips to train and serve Claude.
IREN的AI Cloud平台提供大规模AI训练与推理基础设施。4
IREN’s expansion to 150,000 GPUs builds on its approach to delivering large-scale infrastructure for AI training and inference.

2026年10月27日甲骨文与英伟达宣布拟扩至多吉瓦规模，支持增长中的AI训练、推理和智能体应用需求。1
NVIDIA and Oracle today announced plans to expand Oracle Cloud Infrastructure (OCI) Superclusters with NVIDIA Vera Rubin NVL72 systems to multi-gigawatt scale, supporting growing customer demand for AI training, inference and agentic applications.
Anthropic称2026年Claude的企业与开发者需求加速，同时免费、Pro和Max用户的使用量大幅上升。5
Enterprise and developer demand for Claude has accelerated in 2026, and alongside it we have experienced a sharp rise in consumer usage across our free, Pro, and Max tiers.

甲骨文与英伟达宣布Vera Rubin NVL72及Vera CPU已在OCI正式可用。1
Oracle and NVIDIA also expanded their AI infrastructure collaboration with the general availability of NVIDIA Vera Rubin NVL72 and NVIDIA Vera CPUs on OCI.
Anthropic采用覆盖AWS Trainium、谷歌TPU、英伟达GPU及AMD GPU的多芯片算力架构。2
We have achieved this through our research breakthroughs and our multi-chip compute architecture across AWS Trainium, Google TPUs, NVIDIA GPUs, and AMD GPUs, enabling us to orchestrate workloads to optimize for price and performance.
AMD的Helios将MI455X GPU、EPYC Venice CPU、Pensando网络及ROCm软件集成于AI训练和推理机架平台。3
AMD Helios combines AMD Instinct™ MI455X GPUs, AMD EPYC™ “Venice” CPUs, Pensando™ networking and ROCm™ software in an open, integrated rackscale platform built for large-scale AI training and inference.
IREN已签署超过50,000枚英伟达B300 GPU的采购协议。4
IREN has entered into purchase agreements for over 50,000 NVIDIA B300 GPUs, expanding its total fleet to 150,000 GPUs.