Simplifying the training and deployment of AI models is one of the biggest challenges facing AI developers today. To address this challenge, NXP has partnered with NVIDIA to integrate the NVIDIA TAO APIs directly into NXP’s eIQ machine learning development environment. The NVIDIA TAO low-code AI framework facilitates the use of trained AI models and their fine-tuning for specific applications with transfer learning, while NXP’s eIQ development environment facilitates the deployment of these models to the edge through a combination of software, inference engines, neural network compilers and optimized libraries. Thanks to this integration, customers benefit from accelerated AI development, access to a library of pre-tested AI models and the ability to deploy them on NXP’s broad portfolio of edge processors.
“AI innovation will define the future of the smart connected world. Combining NVIDIA’s expertise in training and testing AI models with NXP’s longstanding experience in industrial and IoT edge innovation creates a synergy that enables our customers to bring their AI models to market quickly and easily,” said Charles Dachs, senior vice president and general manager, Industrial and IoT Edge, NXP.
“NVIDIA TAO greatly simplifies the creation and deployment of AI models, including state-of-the-art generative AI models. This collaboration brings highly accurate, optimized AI models aligned with NVIDIA TAO and seamlessly integrated with NXP’s eIQ development environment to accelerate the deployment of edge AI,” said Deepu Talla, Vice President of Robotics and Edge Computing at NVIDIA.
The NXP eIQ machine learning software development environment enables the deployment of AI algorithms on NXP’s broad portfolio of microcontrollers and microprocessors. It is fully integrated with NXP’s MCUXpresso SDK and Yocto Project Linux development environments, enabling developers to easily develop complete system-level applications.
The eIQ machine learning development environment will directly integrate NVIDIA TAO APIs, providing a single platform for AI training, optimization and model deployment. NVIDIA TAO provides an API-driven workflow that leverages a collection of pre-trained models and transfer learning to enable users to build their own AI models. NVIDIA TAO offers several optimizations, such as model pruning, that increase inference throughput.
For more information on how this collaboration can accelerate development and how NVIDIA’s pre-trained models can run on the NPU (Neural Processing Unit) in NXP SoCs such as the i.MX 93 application processor, visit www.nxp.com/eIQ.
About NXP Semiconductors
NXP Semiconductors N.V. (NASDAQ: NXPI) brings together bright minds to develop breakthrough technologies that make the connected world better, safer and more reliable. As a global leader in secure connectivity solutions for embedded applications, NXP is setting new standards in automotive, industrial & IoT, wireless and communications infrastructure, delivering solutions that enable a more sustainable future. The company has more than 60 years of experience and expertise, employs around 34,200 people in more than 30 countries and generated revenues of $13.28 billion in 2023.
– – – – – –
Further links
👉 www.nxp.com
👉 www.nvidia.com/de-de/
Photo: NVIDIA
