# NVIDIA 展示共封装光学（CPO）交换机视频

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-06-11 02:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmq8ed9fm01p7slld21tj6tbo
- 原文链接：https://x.com/rohanpaul_ai/status/2064769648558756186

## AI 摘要

NVIDIA 发布了与 Lambda 合作的共封装光学（CPO）交换机视频。CPO 将光通信部件移至主网络芯片附近，而非独立可插拔模块。官方博客指出，在 GB300 NVL72 规模下，CPO 通过降低网络功耗和消除大量可插拔光学组件来减少故障点，提升每瓦 token 数。一个 128,000 GPU 数据中心传统需约 655,000 个独立收发器，每个都是潜在故障点，CPO 完全移除该类组件。智能体工作负载需要弹性数据移动，CPO 可减少网络功耗和组件数量，避免 GPU 等待数据。

## 正文

Nvidia released this video of its photonics co-packaged optics （CPO） switch with Lambda.

The AI race is not only about stronger GPUs， but about wasting far less power while those GPUs talk to each other.

With co-packaged optics （CPO）， NVIDIA is putting the light-based communication parts much closer to the main networking chip， instead of placing them as separate plug-in modules at the edge of the switch.

From NVIDIA's official blog on this

"co-packaged optics （CPO） connects directly to the token economy. Network power is overhead： it keeps GPUs connected but doesn't generate tokens. Network failures are also overhead： they turn provisioned GPU capacity into idle capacity. CPO addresses both by reducing network power draw and removing a large class of pluggable optical components from the fabric.

A 128，000-GPU data center using traditional pluggable transceivers requires roughly 655，000 discrete transceiver modules across the switching fabric. Each one is a potential failure point. CPO removes that component class entirely.

Agentic workloads change the pressure on the network. A traditional inference request is relatively self-contained. An agentic request can involve planning， retrieval， tool use， multiple model calls， and follow-up reasoning. More data moving across the cluster. More points where network latency or failure affects the outcome.

Multi-agentic inference needs elastic and resilient data movement， so GPUs are not waiting for data， while maintaining tokens per second and fast time to first token."

### 引用推文

> NVIDIA AI Infrastructure：📣 Get a first look at the NVIDIA Photonics co-packaged optics switch with @LambdaAPI. At NVIDIA GB300 NVL72 scale, the network doesn't just move data between G...