Modal 将在 AI 智能体沙盒中首次采用英伟达 Vera CPU
Modal 在博客中表示，计划让其 Sandboxes 产品——供 AI 智能体运行代码的隔离机器——运行在英伟达 Arm 兼容的 Vera CPU 上，这是其长期完全依赖英特尔与 AMD 处理器后首次转向非 x86 芯片。Modal 基于 50 项智能体编程任务的自建基准测试显示，在容器密度提高的情况下，Vera 可并发处理的任务量最高达到英特尔服务器的两倍，公司将这一表现归因于其高内存带宽，但表示该结果尚未经过独立验证。Modal 上周完成由 Accel 领投的 7.5 亿美元融资，估值 157.5 亿美元；公司称将保留英特尔与 AMD 芯片组成混合集群，且未透露搭载 Vera 的沙盒何时向客户开放。
这一订单是英伟达今年 3 月发布、拥有 88 核的独立 Vera CPU 打入长期由英特尔和 AMD 主导的服务器 CPU 市场的早期信号，Anthropic 与 OpenAI 也已被列为早期用户；不过 Modal 的 2 倍吞吐量仍是未经独立验证的厂商数据。
Last week, NVIDIA hand-delivered Modal’s first Vera CPU server to our SF office. It’s now purring away in a server rack, and we’re pretty excited about what it could mean for Modal Sandboxes and, consequently, Modal users.
Vera is NVIDIA’s new Arm-compatible CPU, built for the Vera Rubin GPU platform but also available as a standalone CPU server.
Supporting Arm would be a huge change for Modal, coming from a long history exclusively running x86 machines. We’d need to make changes across our infrastructure and image build system to support an entirely different CPU architecture, but the benchmarks are impressive: a 2x increase on throughput. With this, the NVIDIA Vera CPU becomes an incredibly compelling option for powering Modal Sandboxes.
Why Vera could be a big deal for Modal
Firstly, multi-tenant clusters are noisy.
Orchestration for a Sandbox product means running hundreds of concurrent containers and VMs on each cloud host. Unlike normal Kubernetes server deployments colocating pods on the same host, the shape of each sandbox workload is unique, and it leads to some interesting dynamics within a multi-tenant cluster:
#Modal#Nvidia#Vera CPU#Intel#AMD#Arm#Accel#Anthropic#OpenAI#Perplexity