This collaboration will see the onboarding of NXP’s advanced AI-focused chips and software tools onto the Aptos platform, a no-code MLOps toolchain that is intended to simplify model development, deployment, and management for low power edge processors.
Eta Compute has completed the integration of NXP’s MCX N Series microcontroller, which includes their eIQ Neutron Neural Processing Unit (NPU) – which is a highly scalable, area and power efficient machine learning accelerator core architecture. This integration will allow Aptos to deeply understand the AI capabilities of the NXP solution. In doing so, Aptos can optimise and adapt AI models specifically for this chip, resulting in model efficiency and performance.
This collaboration marks a significant step towards closing the gap between AI and embedded systems. By eliminating the need to intricately understand the specifics of a chip’s capabilities and constraints, Aptos is intended to empower both ML developers and embedded systems engineers.
AI developers will be able to create and deploy optimised ML models more easily, leveraging NXP’s chips without deep knowledge of embedded techniques to manage tight resources such as on-chip memory and low power requirements, while embedded systems engineers will be able to obtain optimal AI models using no-code toolchains.
