Generative AI Application Development
The Rhino Pi IQ9N has 36GB of onboard LPDDR5 memory and can support on-device deployment of generative AI models such as large language models (LLM) and vision-language models (VLM). This chapter describes how to use the two inference frameworks, AidGen and AidGenSE.
Framework Selection
| Framework | Use Case | Characteristics |
|---|---|---|
| AidGen | Local application integration | Provides a C++ API that can be embedded in your own program |
| AidGenSE | Service-oriented deployment | Provides an HTTP service compatible with the OpenAI API, for easy integration with upper-layer applications |
