MatMoE: Matryoshka Mixture-of-Experts with Dynamic Mixed-Precision Quantization for Efficient Inference

arXiv:2611.01704 · cs.LG, cs.AI · Submitted 2026-11-01 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-11-01

Updated: 2026-11-01

Comments: Accepeted by ICCAD 2026

Code: https://github.com/ggml-org/llama.cpp

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers