d-Matrix adopts NVIDIA NVLink Fusion to bring Raptor XPUs to rack-scale deployment

nordicinst · x · 2026-09-10

Inference chipmaker d-Matrix announced it will use NVIDIA NVLink Fusion to connect its next-generation Raptor XPUs to NVIDIA's AI infrastructure platform, combining NVLink scale-up and Spectrum-X scale-out networking with the NVIDIA MGX rack architecture. CEO Sid Sheth said soaring inference demand meets finite capital, time and energy, and NVLink Fusion offers customers a faster, lower-risk path to deploy and scale ultralow-latency inference in widely deployed liquid-cooled architectures. The move reflects NVIDIA's strategy of opening its platform to third-party silicon vendors.

Original post →

More from Infra

Infra channel →