Ceva inks landmark AI licensing deal, 2 billion devices ship yearly

A major U.S. software and AI platform company has licensed Ceva's NeuPro-M NPU for custom AI silicon, marking one of the most strategically significant licensing agreements in the IP licensor's history.

A major U.S. software and AI platform company licensed Ceva's NeuPro-M neural processing unit for custom AI silicon, signaling a shift as platform companies design their own chips to optimize edge performance and power.

"This is one of the most strategically significant AI licensing agreements in Ceva's history, reflecting the growing role of AI acceleration in shaping the future of computing," Amir Panush, Chief Executive Officer of Ceva, said.

NeuPro-M provides scalable, power-efficient AI acceleration for on-device inference workloads including generative AI, multimodal AI and emerging agentic AI applications. The architecture operates within the power, area and thermal constraints of intelligent edge computing devices, enabling customers to co-optimize performance across the full hardware and software stack. Ceva collaborated closely with the customer to implement advanced neural network optimizations tailored to its target workloads.

Ceva, whose technologies ship in more than 2 billion devices annually across consumer electronics, automotive, industrial IoT and mobile markets, now counts software platform companies among its customers alongside traditional semiconductor firms and device OEMs. The deal positions NeuPro-M as a core architectural element of future intelligent computing platforms, competing with NPU designs from companies including Arm and Synopsys.

Custom AI Silicon Emerges as a Third Computing Layer

Just as CPUs defined general-purpose computing and GPUs accelerated graphics and parallel workloads, AI acceleration is emerging as a third foundational layer of the computing stack, according to Ceva. For companies that own both the operating system and the hardware platform, co-designing silicon and software creates a decisive advantage: tighter OS-to-silicon optimization enables greater performance and power efficiency that off-the-shelf processors cannot deliver, particularly in portable edge computing devices where thermal and battery constraints are unforgiving.

Ceva shares (NASDAQ: CEVA) are expected to react positively to the deal, which extends the company's addressable market beyond traditional chip buyers. The company's NeuPro family of AI NPUs delivers scalable acceleration from ultra-low-power embedded devices to advanced computing platforms, forming a core pillar of Ceva's Physical AI strategy alongside its wireless connectivity and sensing technologies. With more than 400 customers worldwide and 21 billion devices shipped to date, Ceva is positioned to benefit as the custom AI silicon trend accelerates.

This article is for informational purposes only and does not constitute investment advice.