ST. LOUIS, Nov. 17, 2025 /PRNewswire/ -- Moreh, a provider of optimized AI infrastructure software, and Tenstorrent, an AI semiconductor company, are unveiling a scalable, cost-efficient AI data center solution at SuperComputing 2025 in St. Louis, Missouri.

The jointly developed solution combines Moreh's MoAI Framework with Tenstorrent's Galaxy™ Wormhole server and delivers a scalable and cost-effective alternative to traditional GPU-based systems for large-scale AI inference and training. The collaboration addresses one of the biggest challenges in AI infrastructure: the rising cost and operational complexity of AI infrastructure. By combining intelligent software with flexible hardware, the solution enables enterprises and data centers to scale AI inference and training workloads while significantly reducing total cost of ownership (TCO).

Unlike most AI accelerator products that are designed solely for inference, the joint solution uniquely supports both inference and training in a single platform. It offers impressive scalability, allowing data centers to deploy large foundation models with far less networking overhead compared to conventional GPU systems. This enables customers to expand capacity efficiently while achieving substantial reductions in total cost of ownership (TCO). Built through years of partnership between Moreh and Tenstorrent, the joint development combines deep software expertise with advanced chip design to deliver practical benefits for real-world AI deployments.

Through this launch, Moreh expands its support beyond GPUs to include Tenstorrent processors, realizing its vision of becoming a truly universal AI software platform that runs seamlessly across diverse hardware accelerators. Together, Moreh and Tenstorrent are offering a new path toward flexible and cost-efficient AI infrastructure that meets the needs of large-scale AI services.

"Through this partnership, we are bringing the flexibility and efficiency that AI data centers urgently need," said Gangwon Jo, CEO of Moreh. "Our goal is to make scalable AI infrastructure accessible to any enterprise that seeks performance without vendor lock-in."

"Our collaboration with Moreh demonstrates that open, co-designed systems can meet the growing demands of AI at scale," said Jasmina Vasiljevic, Senior Fellow at Tenstorrent. "Together, we're advancing a vision of making AI infrastructure more accessible and infinitely scalable."

About Tenstorrent

At Tenstorrent, we build computers for AI, and the developers that are shaping its future.

Our high-performance RiscV based CPUs and AI, modular chiplets, and scalable compute systems give developers full control, at any scale from a single-node experimentation to data center-scale deployment.

We believe in an open future. Our architecture and software are designed to be edited, forked, and owned. Our team of engineers, dreamers, and first-principle thinkers is redefining how hardware and software converge to accelerate innovation.

[email protected]

View original content to download multimedia:https://www.prnewswire.com/news-releases/moreh-and-tenstorrent-unveil-scalable-cost-efficient-ai-data-center-solution-at-supercomputing-2025-302617060.html

SOURCE Tenstorrent