d-Matrix

d-Matrix powers the next generation of compute for generative AI and large language models with its highly efficient platform designed for AI inference at scale. The company offers a purpose-built solution that scales with model size, making it accessible for companies of all sizes and budgets. Recognizing that AI will consume more energy than the human workforce by 2025, d-Matrix aims to change that trajectory with its innovative technologies. Corsair, their flagship compute platform, is the first of its kind for generative AI, providing up to 20x higher throughput and 20x lower inference latency for large language models (LLMs), along with up to 30x better total cost of ownership (TCO). Corsair features 130 billion transistors and 84TB/s NOC bandwidth and includes a frictionless Software Development Kit (SDK) for easy deployment. The Aviator software stack enhances user experience with broadly adopted open-source software. d-Matrix has offices in Silicon Valley, Sydney, Bengaluru, and Toronto and raised $110 million in Series B funding with backing from Microsoft. The company recently announced the next-gen compute platform Jayhawk II and boasts the Nighthawk Family, the world’s first digital in-memory compute, and the Jayhawk Family, the world’s first BoW chiplet die-to-die interconnect with digital in-memory compute. Their platform accelerates applications powered by transformer models across cloud and enterprise markets, enabling large enterprises to use generative AI for tasks such as customer support, copywriting, code generation, and automated document generation. Small and medium-sized businesses can also harness the power of LLMs and generative AI to automate tasks and discover new work insights. d-Matrix is at the forefront of software and hardware innovation, pushing the boundaries of what is possible.