Related Videos
02:59 
02:25 
02:21
View more videos on: Automotive MCUs, AI/ML
-
Sign In / Register
Sign in for a personalized NXP experience.
-
English
- English
- 中文Chinese
- 日本語Japanese
- 한국어Korean
- Sign in again after changing language
-
Orders
Shopping cart
- Smarter World Videos
- Large Language Models and eIQ® GenAI Flow Explained
Video Player is loading.
Current Time 0:00
/
Duration 2:59
Loaded: 0.00%
0:00
Stream Type LIVE
Remaining Time -2:59
1x
- 2x
- 1.75x
- 1.5x
- 1.25x
- 1x, selected
- 0.75x
- 0.5x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
- en (Main), selected
- 720pHD
- 432p
- 288p
- 180p
- Autoselected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
This is a modal window. This modal can be closed by pressing the Escape key or activating the close button.
This is a modal window. This modal can be closed by pressing the Escape key or activating the close button.
Sign in to access this content and additional site features.
- Apr 7, 2025
About This Video
Large Language Models, or LLMs, are behind the widespread adoption of generative AI services that take the user’s input and generate probable outputs, based on deep learning models. Fine tuning an existing model and using retrieval-augmented generation, or RAG, can yield great context aware results with reduced resource costs.
NXP’s eIQ GenAI Flow provides the tools to bring generative AI to the edge, leveraging the eIQ Neutron NPU in i.MX applications processors. eIQ GenAI Flow uses state of the art open-source AI models optimized and maintained by NXP.
Ready to learn more? Visit nxp.com/LLM
Highlights
- Understand what Large Language Models (LLMs) are, their challenges and how they are optimized for edge applications.
- Learn how retrieval-augmented generation (RAG) fine tunes LLMs.
- See how NXP's eIQ GenAI Flow provides the tools required to bring practical generative AI to the edge, leveraging the eIQ Neutron NPU in i.MX applications processors.