Google 发布 Agent Compute Engine,为每个 Gemini 智能体配独立隔离虚拟机
Google's Agent Compute Engine gives every Gemini agent its own hardware-isolated micro virtual machine
- 1Google 发布 Agent Compute Engine,为每个智能体分配独立虚拟机,已支撑 Gemini,未来数月开放预览
- 2官方称单台服务器可容纳的智能体数量提升 10 倍,20 万智能体测试中挂起与恢复耗时低于 500 毫秒
- 3每个智能体运行在 Titanium 芯片加固的 microVM 中,空闲时自动暂停释放资源,共享内存降低运行成本
- 4治理方面新增 token 追踪与模型路由,支持 Ping Identity、SailPoint 等第三方身份服务,覆盖 Cloud Run 与 GKE
Google 把智能体规模化的成本瓶颈定位在虚拟机层,用硬件隔离加自动挂起换取部署密度,云基础设施竞争开始转向智能体运行效率。
- 影响:若官方密度数字成立,大规模运行智能体的服务器与预算测算方式会改变;token 追踪与第三方身份接入让企业可沿用现有治理体系;服务尚未开放预览,落地节奏以官方时间表为准。
- 参考:可考虑先算出现有智能体部署的单服务器承载量与成本,预览开放后用官方 10 倍密度数字做对照测算;值得盘点企业身份体系与 Ping Identity、SailPoint 等服务的兼容情况。
- 依据:10 倍密度与 20 万智能体低于 500 毫秒挂起恢复均为 Google 官方口径,暂无独立验证;Titanium 隔离与预览时间表出自官方公告。
Google announced Agent Compute Engine, a service that gives each AI agent its own isolated virtual machine. The service already powers Gemini and will open for preview in the coming months. Every agent runs inside a microVM secured by Google's Titanium chip, the company says. When an agent idles, its VM pauses automatically and frees up the machine for others. Shared memory between VMs cuts what each one costs to run. VMs are a pretty huge cost factor when providing agentic systems, so Google is going after efficiency here.
This is also behind the open-sourced Agent Substrate, a Kubernetes runtime. Google says it can fit ten times as many agents on a single server. In a test with 200,000 agents, suspend and resume took less than 500 milliseconds, according to Google. On the oversight side, Google is adding token tracking, model routing, and support for third-party identity providers like Ping Identity and SailPoint. Those controls will extend to Cloud Run, GKE, and managed endpoints.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
来源:The Decoder:AI News · the-decoder.com