d-Matrix develops specialized computing hardware, networking and software for low-latency generative AI inference in data centers. Its digital in-memory compute architecture brings processing closer to memory to address the bandwidth bottlenecks of large language models, aiming to lower power consumption and operating costs. Its platform combines Corsair inference accelerators, JetStream networking and Aviator software, with a 3D-stacked-memory Raptor accelerator in development. Founded in 2019 by Sid Sheth and Sudeep Bhoja, the company is headquartered in Santa Clara and serves enterprise, hyperscale and sovereign AI infrastructure customers.