d-Matrix

d-Matrix's Corsair AI platform is designed for generative AI computing using digital in-memory technology.

In this short talk, d-Matrix CTO Sudeep Bhoja discusses the release of the Deep Seek R1 model, highlighting its impact on inference compute. He discusses the evolution of reasoning models and the significance of inference time compute in enhancing model performance.

d-Matrix lists available careers and benefits and describes its team as expanding.

The company says reasoning and inference-time compute mark an inflection point in AI computing as AI model revenue aligns with compute costs. It also says greater compute can improve results and productivity.

d-Matrix says its Corsair software provides AI solutions accessible to companies of all sizes and budgets.

d-Matrix provides AI computing solutions and information about inquiries and office locations.

d-Matrix develops memory-centric compute for AI inference.

d-Matrix Corp. says its privacy policy explains how it collects, uses, and shares information from users of its website and related services.

At the AI Infra Summit, technology leaders from Amazon Web Services, Qualcomm, d-Matrix, Oracle and Broadcom outline efforts to meet rising AI inference demand. AWS promotes its Graviton CPUs, Qualcomm advances its high-bandwidth compute memory architecture, and d-Matrix plans to integrate its Raptor chip into Nvidia’s rack reference architecture. Oracle and Broadcom focus on networking, while Carrier Global reports an eight-fold increase in token spending this year.

Sep 2026 · SiliconAngleNews article

Dutch chipmaker Euclyd raises more than €200 million ($230 million) in a Series A led by Samsung Electronics, Somerset Capital Partners and Scaleup Europe Fund. It is developing craftwerk, an ASIC designed to run AI agents, with an innovative memory architecture, and plans to ship it in the CWS system for AI clusters exceeding an exaflop. Peter Wennink, former ASML chief executive, joins Euclyd’s board; the company plans to launch its silicon in 2028.

Sep 2026 · SiliconAngleNews article

d-Matrix announces a collaboration with NVIDIA to integrate its next-gen Raptor XPUs into NVIDIA MGX rackscale architecture with NVLink Fusion for ultra-low-latency AI inference. The announcement identifies AI labs, hyperscalers, and neoclouds as the intended users.

Sep 2026 · d-MatrixNews article

d-Matrix acquires Wallaroo.ai, an AI inference deployment and orchestration software company, to speed up deployment of heterogeneous AI inference workloads. The acquisition integrates Wallaroo.ai’s deployment software into d-Matrix’s silicon-to-software data center inference stack.

Aug 2026 · PR NewswireNews article