LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · LambdaMaterial2 min de lecturaEditorial de DisconfirmAI

Cloud Provider Lambda Deploys NVIDIA Photonics Switches: Self-Tests Show 4% Latency Drop; NVIDIA Claims 5x Efficiency Gain

US cloud provider Lambda announced the deployment of NVIDIA Photonics co-packaged optics (CPO) switches in a cluster connecting over 10,000 NVIDIA GB300 GPUs. According to their tests, the solution reduced rack-scale network latency by approximately 4% and lowered the median optical engine temperature from 51°C to 36°C. NVIDIA claims the technology offers up to 5x better power efficiency and 15x higher reliability, though these are general architectural specifications rather than results from this specific deployment.

2026-11-17 00:00 GMT+8

US-based cloud provider Lambda announced on November 16, 2026, that it has deployed NVIDIA Photonics co-packaged optics (CPO) switches in its large-scale AI cluster connecting more than 10,000 NVIDIA GB300 NVL72 GPUs. This move aims to address the high energy consumption and stability issues caused by network bottlenecks in ultra-large-scale AI training.

According to data released by Lambda, compared to traditional pluggable optical modules, the CPO solution reduced network latency by approximately 4% at the rack level and up to 10% at the Pod level, while maintaining the same throughput. In terms of thermal performance, Lambda reported a median optical engine temperature of 36°C in its deployment, compared to 51°C for conventional pluggable optics. Lower temperatures help maintain signal integrity and extend mean time between interruptions (MTBI).

The core of NVIDIA Photonics technology lies in integrating optical engines directly into the switch chip package, replacing traditional pluggable transceivers. This architecture shortens electrical transmission paths and reduces the use of retimer chips. NVIDIA claims the technology offers up to 5x better power efficiency and 15x higher reliability, but these are general specification claims regarding the architecture, not independently verified results from Lambda's specific deployment.

Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

The deployment utilizes liquid cooling to manage heat generated by high-density computing. Each switch features 144 ports running at 800Gb/s and includes 18 field-replaceable external light source modules. This design allows technicians to replace faulty light sources without swapping the entire module, further improving operational efficiency.

Fuentes

  • blogs.nvidia.comNVIDIA Blog↗
Tema

Lambda

美国云服务商Lambda于2026年11月16日宣布,在魁北克园区完成全球首个大规模共封装光学(CPO)部署,使用NVIDIA Photonics交换机连接超10,000颗NVIDIA Blackwell Ultra GPU。据Lambda…

3 pasos1 piezasActualizado 2026-11-19 07:29

Cómo llegó hasta aquí

  1. 2026-11-16Lambda宣布完成全球首个大规模CPO部署,使用NVIDIA Photonics交换机连接魁北克园区的10,000+ NVIDIA Blackwell Ultra GPUs。lambda.com ↗
  2. 2026-11-16NVIDIA博客发布文章,确认Lambda部署细节:每个交换机拥有144个800Gb/s端口,液冷设计,并报告了延迟和温度改善的具体数据。blogs.nvidia.com ↗
  3. 2026-11-17Silicon Report报道指出,相比传统可插拔光模块,CPO在机架规模下延迟降低约4%,在Pod规模下最高降低10%,且吞吐量保持一致。siliconreport.com ↗

Lo que aún está pendiente

  • NVIDIA声称的5倍电源效率提升是否会在长期运行中得到独立第三方验证?
  • Lambda未披露绝对延迟数值和测试流量配置文件,这如何影响与其他网络架构的比较?
  • 现场可更换的外部光源模块在实际运维中的故障率和维护成本表现如何?
Leer el tema completo →
Continuar investigando →