AIThe Registerabout 4 hours ago
ZTE builds a TCO-optimal AI factory to fuel token economy
3 min read
ZTE showcased at MWC Shanghai 2026 an OEX architecture SuperPOD that maximizes tokens per second and lowers total cost of ownership for scaled AI inference. The single rack integrates 128 GPUs and scales to 16,000 GPUs, using a midplane-free, zero-cable design to improve interconnection efficiency and energy efficiency.
Level
Hype check
Tap to vote and see what everyone thinks.
