d-Matrix Adopts NVIDIA NVLink Fusion for Rack-Scale XPU Deployment
d-Matrix is integrating NVIDIA NVLink Fusion to connect its Raptor XPUs to the NVIDIA AI infrastructure platform. This integration enables Raptor XPUs to utilize NVIDIA NVLink scale-up and Spectrum-X scale-out networking within the NVIDIA MGX rack architecture.
Verified State Diff
Impact & Verification Analysis
Enterprise AI infrastructure architects, data center operators, and developers utilizing heterogeneous hardware stacks for inference workloads.
This move signals NVIDIA's strategy to expand its ecosystem dominance by allowing third-party inference chips to function as first-class citizens within the NVIDIA-defined rack-scale infrastructure, reducing vendor lock-in concerns while maintaining NVIDIA's networking standard.
Full Fact Overview
The adoption of NVLink Fusion by d-Matrix represents a strategic shift toward interoperability between third-party AI inference silicon and NVIDIA's proprietary high-speed interconnect fabric. By leveraging NVLink Fusion, d-Matrix's Raptor XPUs gain the ability to interface directly with NVIDIA's scale-up (NVLink) and scale-out (Spectrum-X) networking layers. This architectural integration allows d-Matrix to deploy its inference-optimized hardware within the standardized NVIDIA MGX modular rack design, effectively bridging the gap between specialized inference chips and the broader NVIDIA AI ecosystem.