PG国际

/ Info Center / News / PG INT Launches the PG INT AI Stack to Facilitate On-device AI Deployment with a Fully Manageable Service at CES 2025

PG INT Launches the PG INT AI Stack to Facilitate On-device AI Deployment with a Fully Manageable Service at CES 2025

Las Vegas – January 7th 2025 – PG INT (Stock code:300638), a global leading provider of AIoT solutions and wireless communication modules, announces its brand-new PG INT AI Stack, an integrated set of hardware, AI tools, AI engines, resourceful AI models, offering a fast-to-deploy solution for industry customers to intelligentize their devices with on-device AI. Laying the focus on device-side AI adoption, PG INT AI Stack is designed to address the challenges of diverse demands for intelligent transformation across different industries by providing a complete solution to facilitate the deployment of AI models on smart devices.

Key Capabilities


  • Cross-Platform and Cross-System Flexibility: Leveraging the compatibility with mainstream AI frameworks like TensorFlow, PyTorch, ONNX and MXNet, etc. and the support of multi-tier computing chips and modules, PG INT AI Stack provides the optimal strategy for device-side AI deployment through the integration of an easy-to-deploy code and accessible AI toolchain for data annotation, model training, fine-tuning, achieving high-accuracy and high-speed inference.
  • Powerful On-device AI Engine: PG INT AI Stack’s high-performance inference engine ensures efficient operation, enhancing performance while minimizing power consumption. This aspect is crucial for real-world applications where resources are constrained. Additionally, it supports multi-language SDK interfaces, third-party apps as well as hardware accelerator.
  • Simplifying On-device AI Development: PG INT AI Stack provides an extensive library of AI models (e.g., for audio, CV, LLMs, multimodal LLMs) and provides the value-added model selection and fine-tuning service to help customers to develop industry-oriented models. Therefore, companies of any size can benefit from the manageable service, accelerating on-device AI deployment globally.


The versatility and compatibility of PG INT AI Stack significantly ease the complexity of on-device AI deployments where many terminal devices are constrained with limited computational power and energy efficiency, making it a master tool for the intelligent transformation in smart retail, autonomous vehicles, smart wearables, robotics. It is worth mentioning that PG INT AI Stack works across multiple PG INT AI module and smart module series, supporting the computation power from entry to premium level.

"In the wave of AI-first, we are proudly seeing PG INT leverages AI innovations and in-depth industry expertise to empower the on-device AI deployment with our game-changer PG INT AI Stack, enabling businesses to scale smart devices in various industries with high-efficiency, cost-effective approaches,” said Willson Liu, President of PG INT AI Research Institute. “Looking forward, we are expecting to collaborate with more industry customers to build their smart devices with PG INT-empowered on-device AI solutions and enable a smart future with AI productivity.”

Explore more about PG INT AI Stack, welcome to book a meeting with our sales team or visit us at IMC's booth #10577 in the North hall at CES 2025 from January 7-10.

Related Topics: Edge AI Smart Module
Registered account
Existing account,Sign in now
fsicon.png
The document has been sent to your registered mailbox [email protected] Please check, thank you!
fsicon02.png
You have made an appointment successfully and sent the specific information to your email [email protected] Thank you for your trust!
20200520175738392.jpg

Hi there! 👋 What can we help you today?

网站地图