#npu

Lemonade packages local AI inference behind an OpenAI-compatible server that targets GPUs and NPUs, aiming to make open models easier to deploy on everyday PCs.

Community discussion in LocalLLaMA pointed to a March 11, 2026 FastFlowLM and Lemonade update that brings Linux support to AMD XDNA 2 NPUs, including setup guidance for Ubuntu and Arch systems.

A developer with a Mac Mini M4 used Claude to reverse engineer Apple's private Neural Engine APIs, bypassed CoreML, and successfully trained a 110M parameter Microgpt model entirely on the ANE — opening new possibilities for NPU-based AI training.