← sources

Research paper: MawForge: Memory-Bounded Expert Materialization for Local Mixture-of-Experts Inference

source: semantic-scholarpublished 2026-06-17 00:00ingested 2026-07-22 08:15

retained text

Query: mixture of experts inference serving
Authors: Craig Opie
Citations: 0
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 tests a different systems hypothesis: local MoE serving can be made practical on constrained unified-memory machines by storing the full model on disk, keeping common tensors resident, and materializing routed expert tensors into a bounded execution cache on demand. The central finding is that MawForge is effective as a bounded execution mechanism and measurement substrate for local MoE inference, but not as a cache-maximization policy. Performance depends on balancing expert reuse against resident footprint, KV-cache size, quantization, route locality, and macOS memory pressure.

document fetched 2026-08-10 07:17 · canonical https://semanticscholar.org/paper/655058c7763acebc42cb1cf60e8526d1ec126b84