Chip startup d-Matrix has closed a $275 million Series C funding round, valuing the company at $2 billion.

The round was co-led by a global consortium comprised of Bullhound Capital, Triatomic Capital, and Temasek, and also saw participation from the Qatar Investment Authority (QIA), EDBI, M12, Microsoft’s Venture Fund, Nautilus Venture Partners, Industry Ventures, and Mirae Asset.

It brings the total raised by d-Matrix to $450 million, which the company said it will use to advance its roadmap, accelerate global expansion, and support multiple large-scale deployments of its data center inference platform.

Founded in 2019 and headquartered in Santa Clara, d-Matrix develops accelerator cards that aim to make AI inferencing workloads quicker and more efficient. Its full-stack platform is powered by the company’s Corsair inference accelerators, JetStream NICS, and Aviator software, which it claims can deliver 10X faster performance, 3X lower cost, and 3–5X better energy efficiency than GPU-based systems.

Taking the form of a standard PCIe card with both single-card and dual-card configurations, Corsair embeds its processing components into the memory, an approach known as in-memory compute. Its single-card configuration provides up to 256GB of off-chip capacity memory and 2GB of performance memory at 150Tbps, while the dual configuration offers up to 512GB of off-chip capacity memory and 4GB of performance memory at 300Tbps.

In a statement, d-Matrix said its offering provides a “clear path to reducing global data center energy consumption,” enabling companies to deliver “cost-efficient, profitable AI services without compromise.”

“From day one, d-Matrix has been uniquely focused on inference. When we started d-Matrix six years ago, training was seen as AI’s biggest challenge, but we knew that a new set of challenges would be coming soon,” said Sid Sheth, CEO and co-founder. “We predicted that when trained models needed to run continuously at scale, the infrastructure wouldn’t be ready. We’ve spent the last six years building the solution: a fundamentally new architecture that enables AI to operate everywhere, all the time. This funding validates that vision as the industry enters the Age of AI Inference.”