SynopsisArtificial intelligence workloads have been shifting from training AI models to running them for everyday use, a process known as inference. While Nvidia's pricey graphics processors dominate training workloads, d-Matrix specializes in inference.AgenciesD-Matrix said on Thursday it will adopt Nvidia's chip-linking technology to use the startup's processors directly inside the semiconductor giant's data-center systems as demand for AI intensifies.Artificial intelligence workloads have been shifting from training AI models to running them for everyday use, a process known as inference. While Nvidia's pricey graphics processors dominate training workloads, d-Matrix specializes in inference.D-Matrix's new chips, called Raptor, will plug into Nvidia's server racks using NVLink Fusion, a technology that has connectors and specialized memory so custom AI chips can plug into Nvidia's larger data-center systems, the startup said.The Nvidia-compatible racks are expected to be available in 2027, with the Raptor chips scheduled to complete their final design stage by the end of this year.D-Matrix said the combined systems are aimed at fast, low-latency AI services such as coding assistants, chatbots and voice agents, where speed is critical.The startup did not disclose the financial terms of the collaboration.The Santa Clara, California-based startup is also partnering with connectivity firm Astera Labs to build custom solutions to ensure fast data flow across the system.Microsoft has backed d-Matrix since its $110 million financing round in 2023. The startup, which shipped its first AI chip in November 2024, was valued at $2 billion when it raised $450 million last year. ...moreElevate your knowledge and leadership skills at a cost cheaper than your daily tea.Subscribe Now
Nvidia: Chip startup d-Matrix to use Nvidia chip-linking tech in AI servers - The Economic Times
Artificial intelligence workloads have been shifting from training AI models to running them for everyday use, a process known as inference. While Nvidia's pricey graphics processors dominate training workloads, d-Matrix specializes in inference.
d-Matrix integrates Raptor inference chips into Nvidia servers via NVLink Fusion; 2027 launch from $2B startup. Nvidia opens infrastructure to custom accelerators, eroding GPU proprietary advantage and requiring IT leaders to evaluate mixed-silicon inference stacks.










