The A.I. Daily
d-Matrix adopts NVIDIA NVLink Fusion for XPU racks
Inference chipmaker d-Matrix will use NVIDIA NVLink Fusion to connect its Raptor XPUs to NVIDIA’s AI platform and MGX rack architecture, easing rack-scale deployment. NVLink Fusion claims 3x lower XPU-to-XPU latency versus Ethernet, 10x higher packet rates, and 3 TB/s per XPU all-to-all bandwidth.