Next-generation d-Matrix inference XPU for NVLink Fusion racks
d-matrix.ai/announcements/d-matrix-rackscale-nvidia
Raptor is d-Matrix's next-generation inference XPU. Company announcements describe it as designed for integration with NVIDIA NVLink Fusion and MGX rack-scale infrastructure, with tape-out expected before the end of 2026 and integrated systems planned later.