NVIDIA blog: d-Matrix to connect Raptor XPUs via NVLink Fusion

10 Sep 2026: NVIDIA published that inference chipmaker d-Matrix will use NVLink Fusion to connect its next-generation Raptor XPUs to NVIDIA’s AI infrastructure platform — MGX racks, Spectrum-X, and related stack. Company blog is the primary. Performance and scale claims stay NVIDIA’s / d-Matrix’s.

10 Sep 2026: NVIDIA published “d-Matrix Adopts NVIDIA NVLink Fusion for Rack-Scale XPU Deployment.” d-Matrix will use NVLink Fusion to connect its next-generation Raptor XPUs to NVIDIA’s AI infrastructure platform. That dated NVIDIA blog is the filing event.

NVIDIA: the path includes NVLink scale-up, Spectrum-X scale-out, the MGX rack architecture, and the broader NVIDIA AI platform — framed as an accelerated, lower-risk route from custom silicon to large-scale deployment. That framing is NVIDIA’s.

Sid Sheth, d-Matrix cofounder and CEO, quoted on NVIDIA’s page: “Demand for inference is soaring, but capital, time and energy remain finite.” He said NVLink Fusion and MGX let the company integrate Raptor XPUs into a broadly deployed, liquid-cooled architecture for a faster, lower-risk path to deploy and scale ultralow-latency inference.

NVIDIA: NVLink Fusion lets silicon companies connect custom XPUs and CPUs into the NVIDIA stack. d-Matrix plans a single high-bandwidth, low-latency scale-up domain, and racks that can work alongside GPU systems such as NVIDIA Vera Rubin NVL72 for disaggregated inference. NVIDIA’s description of the plan.

Planned integrations named on the same post: NVIDIA Vera CPUs, ConnectX-9 SuperNICs, BlueField-4 DPUs, and Spectrum-X Ethernet. Treat that as NVIDIA’s description of d-Matrix’s plan — not a shipped customer deployment count.

A dated NVIDIA primary puts another specialized inference XPU vendor on the NVLink Fusion / MGX path — concrete named interconnect + rack stack for custom silicon beside GPU factories. Commercial schedule and performance stay the companies’ framing.