The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
By Yuanteng Chen, Peisong Wang, Yuantian Shao, Nanxin Zeng, Chang Xu, Jian Cheng
The paper studies how the design of Mixture-of-Experts (MoE) routers affects inference speed when combined with Speculative Decoding (SD). It shows that routers promoting high expert coactivation reduce memory transfer costs and improve runtime. By integrating a global load‑balancing loss, shared experts, a consistency loss, and an autoregressive expert selection mechanism, the authors achieve a 21% throughput gain over baseline MoEs while preserving accuracy.
By Kumari Nishu, Han-Byul Kim, Santosh Chilkunda, Maxwell Horton, Arnav Kundu, Mohammad Samragh, Lauren Hannah, Mohammad Sekhavat, Nikhil Bhendawade, Manuel Ciosici, Iman Mirzadeh, Keivan Alizadeh Vahid, David Harrison, Irina Belousova, Mehrdad Farajtabar, Minsik Cho
arXiv:2608. 11688v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are attractive for edge deployment because they provide high model capacity while activating only a small subset of parameters per token, improving compute efficiency.
By Alish Kanani, Layan Badawi, Umit Y. Ogras
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
By Gongli Zhang, Zhulin Liu, C. L. Philip Chen
arXiv:2609.36222v1 Announce Type: new
Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
By Ali Abbasi, Justin Shi, Soheil Kolouri
Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrain...
arXiv:2602. 06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.
By Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar, Samuel Horvath
arXiv:2510. 19366v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs).
By Xinfeng Xia, Xiaofeng Hou, Jiacheng Liu, Wenfeng Wang, Mingxuan Zhang, Peng Tang, Chao Li, Minyi Guo
arXiv:2607. 08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices.
By Ali Kayyam
PCoMoE introduces a path‑compositional execution framework that moves Mixture‑of‑Experts inference from coarse‑grained expert selection to fine‑grained path composition. It uses a path‑level formulation of expert computation, a compatibility‑aware layer‑wise pruning strategy to eliminate low‑value path combinations, and a hardware‑friendly execution engine that reuses sub‑expert structures with bounded overhead. Experiments show up to a 1.31× speedup and a 10% accuracy improvement over existing MoE inference methods.
By Ziyan Gan, Fangxin Liu, Chenyang Guan, Junjie Wang, Ning Yang, Haomin Li, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Zongwu Wang, Li Jiang, Haibing Guan
arXiv:2608.21614v1 Announce Type: new
Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases de...
By Yujie Zhang, Bin Gao, Tulika Mitra
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU.