arXiv cs.LG
· Papers
MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference
arXiv:2607.09686v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) language models separate total parameter count from per-token active computation, but local inference systems often still require the full model, key-value cache, runtime buffers, and operatingsystem headroom to fit in fast memory. MawForge