en.Wedoany.com Reported - Fabless semiconductor company MemryX Inc. has recently expanded its Cascade deployment platform family with three new products based on the MX3 accelerator architecture, designed to address the multiple challenges developers face in power consumption, memory bandwidth, deployment complexity, and infrastructure costs as AI migrates from the cloud to factories, transportation systems, robots, and smart infrastructure. These products were showcased at the Automate 2026 exhibition held at McCormick Place in Chicago, USA.
The MemryX Cascade 100P PCIe accelerator is designed for high-density edge server deployments and multi-camera AI applications. Based on a 16-chip MX3 processor array, it enables parallel inference on hundreds of real-time video streams. The card features a single-slot, passive cooling form factor that can be integrated into standard server environments without adding complex thermal management or power budget constraints, making it suitable for scenarios such as smart manufacturing, intelligent transportation, video analytics, and multi-camera AI deployments.
The MemryX Cascade 100U USB accelerator provides AI acceleration to existing systems via a standard USB Type-C connection, equipped with two MX3 accelerators. Developers can quickly evaluate, prototype, and deploy AI vision applications without redesigning existing hardware platforms.
The MemryX Cascade 100R Raspberry Pi HAT+ is designed specifically for the Raspberry Pi ecosystem, bringing hardware-accelerated AI inference to robotics, machine vision, education, and low-power industrial applications. This HAT is based on two MX3 processors connected via PCIe and can be daisy-chained to support larger-scale AI deployments.
All three products are supported by the MemryX Developer Hub, providing a unified software environment for compiling and deploying AI models across the MX3 product family. MemryX CEO Ross Jatou stated that whether developers are prototyping on a Raspberry Pi, adding AI acceleration to existing systems via USB, or deploying hundreds of video streams on edge servers, they need a common architecture to scale seamlessly while delivering performance without the power and memory penalties of traditional approaches. The expanded Cascade platform family enables customers to transition from development to production based on a single, scalable, and efficient AI architecture powered by MX3.
Attendees of Automate 2026 can visit Booth 15045 until June 25 to learn more about the Cascade product family.
MemryX Inc. is a fabless semiconductor company focused on AI inference acceleration, featuring a production-proven "at-memory" dataflow architecture. The company has secured $44 million in Series B funding from investors including HarbourVest, NEOM Investment Fund (NIF), Arm IoT Fund, eLab Ventures, M Ventures, and Motus Ventures, with its headquarters located in Ann Arbor, Michigan.
This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com
