What's New
Simple
Processing
MemryX’s Edge AI solution enables one click compilation and performance optimization of models. No hand tuning or model retraining is required. MemryX Edge AI optimally configures for your trained AI model(s) – with one click.
Scalable
Processing
One MemryX chip offers a lot of AI processing power. But if you need more performance or lower latency, simply linearly cascade any number of our AI Processing chips. Each die is a chiplet, and you can use the same software to process multiple models in one chip or large model(s) across multiple chips.
Forward
Architecture
MemryX uses a proprietary, configurable native dataflow architecture, along with at-memory computing that sets the bar for Edge AI processing. The system architecture fundamentally eliminates the data movement bottleneck, while supporting future generations (new hardware, new processes/chemistries and new AI models) — all with the same software.
Markets
News
Check out animation for the basics of choosing MemryX
MemryX Announces Production Availability of the MX3 Edge AI Accelerator **Ann Arbor, MI – October 1, 2024** – MemryX, a leading innovator in AI accelerators for Edge applications, today announced production availability of MX3 Edge AI Accelerator. Available today as both as a standalone chip and a 4-chip 2280 M.2 Module, the MX3 offers industry […]
Not all AI accelerators are built the same. Find out some of the differences and questions to ask. Guarantee you’ll be a lot more aware of this excited new field after you give it a listen. Bonus: You might even learn something about Independence Day for two countries!
Join us for industry insight from Unigen. Oliver discusses his company and solutions, including the AI accelerator industry. Stay tuned for ending discussion where the topic is Newark
Join Tim and Alan, with special guest, Mohamed Haidara, as they discuss Model Zoo definition and approaches, MemryX compilers, and the best history lesson you will ever receive on YOLO versions, past and present.