Nvidia Wants to Own Every Chip Inside AI Data Centers
Nvidia Wants to Own Every Chip Inside AI Data Centers
英伟达希望掌控人工智能数据中心内的每一颗芯片
Nvidia is hyping up its new Vera Rubin chip system this week, revealing new performance benchmarks for the GPU and CPU combo ahead of rival AMD’s annual product event in San Francisco on Thursday. 本周，英伟达（Nvidia）正在为其全新的 Vera Rubin 芯片系统造势，并在竞争对手 AMD 周四于旧金山举行年度产品发布会之前，公布了该 GPU 与 CPU 组合的全新性能基准测试数据。
During a lengthy technical workshop last week at the company’s headquarters in Santa Clara, California, Nvidia executives boasted to a small group of journalists about the chip system’s increased power and efficiency capabilities. The biggest takeaway: Nvidia, which has long specialized in making GPUs, is increasingly trying to position itself as a supplier of CPUs that can power AI agents. 在上周于加州圣克拉拉公司总部举行的一场长时间技术研讨会上，英伟达高管向一小群记者展示了该芯片系统在功耗和效率方面的提升。最核心的信息是：长期专注于 GPU 制造的英伟达，正日益试图将自己定位为能够驱动 AI 智能体的 CPU 供应商。
While GPUs are still the main hardware that companies use to train and run their AI models, the industry’s shift toward more complex, agentic systems has increased demand for CPUs, which can orchestrate data flows, networking, and other software tasks. That’s likely one reason Nvidia has been eager to promote itself as a supplier of complete AI systems rather than just AI chips. 尽管 GPU 仍然是企业训练和运行 AI 模型的主要硬件，但行业向更复杂、更具自主性的智能体系统转型，增加了对 CPU 的需求，因为 CPU 可以协调数据流、网络及其他软件任务。这很可能是英伟达急于将自己宣传为完整 AI 系统供应商，而不仅仅是 AI 芯片供应商的原因之一。
Vera Rubin is Nvidia’s successor to its hybrid superchip system Grace Blackwell and represents the linchpin of its near-term future powering the AI industry. It’s designed to offer one CPU for every two GPUs. In a single Vera Rubin NVL 72 super chip system, there are 36 Vera CPUs for every 72 Rubin GPUs. Nvidia is also selling the Vera CPU as a stand-alone product, and it has reportedly told Chinese customers these could be ready as soon as August. Vera Rubin 是英伟达混合超级芯片系统 Grace Blackwell 的继任者，也是其近期驱动 AI 行业发展的核心支柱。它的设计目标是每两个 GPU 配备一个 CPU。在单个 Vera Rubin NVL 72 超级芯片系统中，包含 36 个 Vera CPU 和 72 个 Rubin GPU。英伟达还将 Vera CPU 作为独立产品销售，据报道，该公司已告知中国客户，这些产品最早可能在 8 月份准备就绪。
Nvidia executives emphasized that its new Vera Rubin NVL72 racks—a stack of chips packed into a single liquid-cooled platform—are much more “plug-and-play” than some of its earlier products. During a brief tour of a Nvidia data center lab in Silicon Valley, Nvidia executives shared that OpenAI already has one Vera Rubin rack in use. 英伟达高管强调，其全新的 Vera Rubin NVL72 机架（将多颗芯片集成在单一液冷平台中的堆叠系统）比其早期产品更具“即插即用”的特性。在参观硅谷的一处英伟达数据中心实验室期间，英伟达高管透露，OpenAI 已经投入使用了一台 Vera Rubin 机架。
Nvidia CEO Jensen Huang didn’t make an appearance at the workshop in Santa Clara last week; he was in Japan announcing the chipmaker’s new partnerships with a number of Japanese firms to develop AI for robotics. The briefings were instead led by Ian Buck, Nvidia’s longtime vice president of accelerated computing and the architect behind the company’s CUDA software. 英伟达首席执行官黄仁勋（Jensen Huang）并未出席上周在圣克拉拉举行的研讨会；他当时正在日本，宣布该公司与多家日本企业建立新的合作伙伴关系，共同开发机器人 AI 技术。此次简报会由英伟达加速计算部门资深副总裁、CUDA 软件架构师 Ian Buck 主持。
“We’re on a road map to crank out new architectures, not just GPUs but CPUs,” Buck told reporters. “We’re going to keep innovating, because it’s do this or die in Silicon Valley.” “我们正按照路线图推出新的架构，不仅是 GPU，还有 CPU，”Buck 对记者表示。“我们将持续创新，因为在硅谷，不创新就意味着死亡。”
The meetings were held in Huang’s executive briefing center, where multiple desks nearby were piled with bags of Taiwanese snacks that the CEO brought back from his recent trip to Computex, a massive annual semiconductor trade show in Taipei, an Nvidia spokesperson told WIRED. 英伟达发言人告诉《连线》（WIRED）杂志，会议在黄仁勋的行政简报中心举行，附近的多张桌子上堆满了这位 CEO 从台北国际电脑展（Computex，台北一年一度的大型半导体贸易展）带回的台湾零食。
Nvidia claims that the Vera Rubin NVL72 system will process 10 times as many tokens per watt as the company’s Grace Blackwell super chip. The company says that its Vera CPU is faster at processing agentic AI tasks compared to rival CPUs from AMD and Intel (though the tests it ran to support those benchmarks appears to have used slightly older generations of its competitors’ CPUs). Localized memory subsystems on the new chips will also offer nearly three times as much memory bandwidth as Blackwell, which will likely be an appealing feature to many companies amid an ongoing shortage of high-bandwidth memory. 英伟达声称，Vera Rubin NVL72 系统每瓦处理的 Token 数量将是其 Grace Blackwell 超级芯片的 10 倍。该公司表示，与 AMD 和英特尔的竞争对手 CPU 相比，其 Vera CPU 在处理智能体 AI 任务时速度更快（尽管用于支持这些基准测试的测试似乎使用了竞争对手较旧一代的 CPU）。新芯片上的本地化内存子系统提供的内存带宽也将是 Blackwell 的近三倍，在当前高带宽内存持续短缺的情况下，这对许多公司来说可能是一个极具吸引力的特性。
Nvidia says it has also significantly reduced the number of cables needed to connect its chips to racks in multi-rack server systems, to the point where the company is touting Vera Rubin as “cable-free compute” and “hot-swappable.” This means customers can theoretically reduce the amount of time it takes to install each rack from a couple of hours to a few minutes, a point that was brought up by both Buck and Andrew Bell, Nvidia’s senior vice president of hardware engineering. And the new chip system is 100 percent liquid-cooled, which can reduce the amount of energy needed to cool the chips, since air-cooling is more energy intensive. 英伟达表示，它还显著减少了多机架服务器系统中连接芯片与机架所需的线缆数量，以至于该公司将 Vera Rubin 宣传为“无缆计算”和“热插拔”。这意味着客户理论上可以将安装每个机架所需的时间从几个小时缩短到几分钟，这一点由 Buck 和英伟达硬件工程高级副总裁 Andrew Bell 共同提出。此外，该新芯片系统采用 100% 液冷技术，由于风冷系统能耗更高，液冷可以有效降低芯片冷却所需的能源。
Ever since Nvidia unveiled Vera Rubin in the spring of 2025, the company has been slowly dribbling out more details about the chip system while insisting it will be released on schedule. Huang has repeatedly said Vera Rubin is ramping to “full production” and will ship in the second half of this year, with early customers including Microsoft, OpenAI, and Oracle. 自 2025 年春季英伟达发布 Vera Rubin 以来，该公司一直在缓慢披露有关该芯片系统的更多细节，并坚称将按计划发布。黄仁勋多次表示，Vera Rubin 正处于“全面生产”的爬坡阶段，并将于今年下半年出货，早期客户包括微软、OpenAI 和甲骨文（Oracle）。
Nvidia is particularly sensitive to any suggestion of delays after its previous-generation Blackwell chips reportedly overheated when connected together in the company’s customized server racks, forcing it to make design changes and push back shipments. 在有报道称其上一代 Blackwell 芯片在公司定制的服务器机架中连接时出现过热，迫使其进行设计更改并推迟出货后，英伟达对任何有关延迟的暗示都格外敏感。
Nvidia’s marketing push for Vera Rubin is happening just ahead of rival AMD’s annual conference, where executives are expected to tout its next-generation AI and data center chips. On Sunday, AMD revealed more details about its Helios AI chip rack, which is designed to compete with Nvidia’s new wares. Both AMD and Nvidia have been vying for large-scale, multiyear contracts to supply chips to AI hyperscalers like Meta and Amazon and AI labs like OpenAI, Anthropic, and SpaceXAI. 英伟达对 Vera Rubin 的营销推广正值竞争对手 AMD 年度大会前夕，预计 AMD 高管将在会上推介其下一代 AI 和数据中心芯片。周日，AMD 披露了其 Helios AI 芯片机架的更多细节，该产品旨在与英伟达的新品竞争。AMD 和英伟达都在争夺大规模、多年期的芯片供应合同，以服务于 Meta 和亚马逊等 AI 超大规模云服务商，以及 OpenAI、Anthropic 和 SpaceXAI 等 AI 实验室。
Over the past two years, AMD has significantly grown its share of the market for CPUs used in data centers. The company has long been recognized as a pioneer of the modern chiplet architecture used in x86 processors, which still account for the vast majority of data center CPU revenue. Nvidia, by contrast, builds its data center CPUs on ARM, an alternative chip architecture known for its power efficiency. 在过去两年中，AMD 在数据中心 CPU 市场份额上取得了显著增长。该公司长期以来被公认为 x86 处理器所采用的现代小芯片（chiplet）架构的先驱，而 x86 处理器目前仍占据数据中心 CPU 收入的绝大部分。相比之下，英伟达则基于 ARM 构建其数据中心 CPU，这是一种以能效著称的替代性芯片架构。
Nvidia executives Buck and Hannah Coutand, who runs Nvidia’s CPU product marketing, both emphasized that Vera Rubin abandons the chiplet architecture used by many modern processors in favor of a single, monolithic chip. Coutand argued that stitching together multiple chiplets imposes “a heavy tax on memory bandwidth and data movement,” whereas the monolithic design of Vera Rubin allows data 英伟达高管 Buck 和负责 CPU 产品营销的 Hannah Coutand 都强调，Vera Rubin 放弃了许多现代处理器所使用的小芯片架构，转而采用单一的单片式（monolithic）芯片设计。Coutand 认为，将多个小芯片拼接在一起会“对内存带宽和数据传输造成沉重负担”，而 Vera Rubin 的单片式设计则允许数据……