iohann.s.titov@gmail.com Ivan S. Titov OpenFlowLM is a community fork of FastFlowLM, the NPU-first LLM runtime for AMD Ryzen AI (XDNA2) processors. For most of its LLM families it replaces the closed NPU kernels with open AIE designs compiled from source with the IRON/mlir-aie toolchain. Families without an open design yet (vision, audio, Gemma 4, GPT-OSS, Whisper) still use FastFlowLM's closed kernels. Atomic-Germ/OpenFlowLM-Next https://github.com/Atomic-Germ/OpenFlowLM-Next/issues