04:00
2026-07-14
arxiv.org
machine-learning
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
A new systems approach called MawForge, detailed in arXiv:2607.09686v1, makes local inference of sparse Mixture-of-Experts (MoE) language models practical on constrained unified-memory machines by sto…