ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
AI infrastructure startup d-Matrix will integrate NVIDIA's NVLink Fusion interconnect into its upcoming Raptor accelerators. The deal lets d-Matrix scale to 144 Raptor XPUs per rack using NVIDIA's MGX reference designs, Vera CPUs, and BlueField DPUs. Each Raptor card features 32 GB of 3D-stacked DRAM with 100 TB/s of memory bandwidth.
Tap to vote and see what everyone thinks.
Summary by ByteBrief