Roofline brings Mixture-of-Experts to the Edge: MoE Compiler Support in IREE
Mixture-of-Experts (MoE) can accelerate LLM inference by an order of magnitude compared to dense LLMs of similar size, by activating only the parts of the model selected for a given token. This is why all frontier labs are training MoE models, and these models are now moving to the edge. But while the hardware is ready, the software is not. Current edge AI compilers do not support the dynamic expert routing that MoE depends on. Roofline closes this gap by bringing native MoE support to its IREE-based deployment stack.