Introducing Lemonade Server: Local LLM Serving with GPU and NPU Acceleration

Описание: In this video, we introduce Lemonade Server—a powerful tool that lets you deploy local large language models (LLMs) directly on your PC. With support for industry-standard APIs, Lemonade Server easily connects to a wide range of applications, enabling you to replace cloud-based LLMs with fast, private, local alternatives.

🔧 What You’ll See

How to install and set up Lemonade Server
Downloading, managing, and prompting LLMs
Exploring key resources: GitHub repo, documentation, model details, and featured apps

🖥️ Test Setup
We demonstrate everything using an AMD Ryzen™ AI 395+ Mini PC with 128GB of RAM, showcasing the performance and flexibility of local inference.

Whether you're a developer, researcher, or enthusiast, this walkthrough will help you get started with local LLMs in minutes.

Links Referenced in the Video:
Lemonade Server: https://lemonade-server.ai
Local LLM Servers: https://lemonade-server.ai/docs/serve...

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

Find Ryzen AI Software 1.5 documentation:
https://ryzenai.docs.amd.com/en/lates...

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

***

© 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.