Nvidia intends to invest in d-Matrix, the Santa Clara-based inference chip startup valued at $2 billion after its November 2025 Series C round, The Information reported, citing three people with knowledge of the deal.

The planned investment forms part of Nvidia's effort to make its technology compatible with rival chip designs, according to the report. Neither company has confirmed the size of the stake.

The move comes roughly a month after d-Matrix announced it would adopt Nvidia's NVLink technology to connect its Raptor processors with Nvidia hardware in rack-scale solutions.

What is NVLink Fusion?

Nvidia first unveiled NVLink Fusion in May 2025. The interconnect technology lets partners build semi-custom AI infrastructure that links non-Nvidia accelerators with Nvidia hardware.

The partner roster already includes:

• Arm
• Fujitsu
• Intel
• MediaTek
• Qualcomm
• SiFive
• Synopsys

What does d-Matrix build?

Founded in 2019 and headquartered in Santa Clara, d-Matrix develops accelerator cards designed to make AI inferencing workloads faster and more efficient. Its full-stack platform combines three components:

• Corsair inference accelerators
• JetStream NICS
• Aviator software

The company claims the stack delivers 10X faster performance, 3X lower cost, and 3–5X better energy efficiency than GPU-based systems.

How much money is involved?

In November 2025, d-Matrix closed a $275 million Series C round at a $2 billion valuation.

The Information separately reported in July 2026 that the startup was seeking additional financing, targeting a $5 billion valuation. That would more than double the company's worth in under two years if the round closes at the target figure.

A direct Nvidia investment would place d-Matrix among the chipmaker's portfolio of companies building silicon that interoperates with, rather than only competes against, its own accelerators. The deal has not closed, and terms remain unreported.