Lemonade Server & Open WebUI - Local LLM Serving with GPU and NPU Acceleration

Опубликовано 31 июля 2025, 16:30

In this video, we show how you can easily integrate Lemonade Server with Open WebUI to unlock powerful local LLM capabilities on your Ryzen AI PC. From running Python code and rendering HTML to generating 3D visuals—all within a single interface.

🔧 What You’ll See
How to install and configure Open WebUI for use with Lemonade Server
How to generate and execute Python code—including dynamic plotting
How to render and interact with 3D HTML content locally
🖥️ Test Setup
We’re running everything on a Ryzen AI 395+ Mini PC with 128GB RAM, demonstrating the performance and flexibility of local inference with GPU and NPU acceleration.

Links Referenced in the Video:
Lemonade Server: lemonade-server.ai
Open WebUI Guide: lemonade-server.ai/docs/server...

Find the resources you need to develop using AMD products: amd.com/en/developer.html

Have questions or ideas? Collaborate directly with developers and experts on the AMD Developer Community Discord:
discord.gg/2tYF7hqW

***

© 2025 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, EPYC, ROCm, and AMD Instinct and combinations thereof are trademarks of Advanced Micro Devices, Inc.