chiprook
← Hardware
HardwareOctober 3, 2026, 17:00

Zinc Whiskers Under Raised Floor Caused Failure of 128-Rack AI Cluster

At a 2 MW AI data center with 128 racks of liquid-cooled servers running eight Nvidia H100 GPUs each, zinc whiskers from galvanized floor supports entered servers and triggered short circuits, ECC errors and GPU resets. Recovery required board replacements, particle filters and replacing zinc-plated components.

Zinc Whiskers Under Raised Floor Caused Failure of 128-Rack AI Cluster
#Nvidia#H100
Read next
Hardware

CoreWeave Connects Hundreds of Rubin GPUs in One Multi-Rack Cluster

Hardware

Nvidia roadmap shifts to rack-scale AI with Rubin Ultra

Hardware

Pat Gelsinger-backed PicoJool raises $27.5M for AI cluster optical interconnects

Hardware

Lightmatter launches optical module that halves fiber cabling in AI clusters