The board is designed to bring AI inference acceleration to edge servers and industrial vision systems.
Leveraging a dynamic TPU array architecture, the InferX X1 is designed around low latency processing of Batch=1 workloads with a special focus on challenging Edge Vision applications.
The InferX X1 remains flexible to allow customers to migrate to new AI models in the future and adapt to changing system requirements and protocols.
The InferX X1P1 board offers AI inference acceleration for edge AI workloads such as Yolov3.
The InferX X1P1 board is available in production quantities starting in November 2021 and is priced starting at $399 for single unit quantities.
Flex Logix also offers a software toolkit to support customer model porting to the X1P1 board.