Hardware · Jul 7
Nvidia Kyber NVL144 Delay to 2028 Shows AI Scaling Has a PCB Manufacturability Bottleneck
The reported rack slip turns the spotlight from GPU specs to the stubborn physics of building a Vera Rubin Ultra midplane at scale.
- Watch rack manufacturability, not just GPU specs, when planning AI capacity.
- Treat analyst reported delays as risk signals until Nvidia provides official guidance.
- Ask suppliers about midplane yield, rack volume timing, and serviceability before locking cluster plans.