The recent release of Lemonade 10.0.1 aims to simplify the configuration of AMD Ryzen AI NPUs for running large language models (LLMs) on Linux systems.

AMD Ryzen AI Support

With the release of Lemonade SDK 10.0 and FastFlowLM 0.9.35 earlier this month, the use of AMD XDNA 2 NPUs on Linux has become a concrete reality for LLM inference workloads. Lemonade 10.0.1 introduces refinements to the installation process of this open-source solution for local LLMs.

For those evaluating on-premise deployments, there are trade-offs to consider carefully. AI-RADAR offers analytical frameworks on /llm-onpremise to evaluate these aspects.