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: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:2606. 15453v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost.
By Yingnan Zhao, Razvan Bunescu, Ahmed Louri, Avinash Karanth, Ke Wang
arXiv:2606. 01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge.
By Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu, Yinglong Xia, Qiang Zhang, Qifan Wang, Ren Chen, Dongqi Fu, Jiayi Liu, Zhoukai Zhao, Xiangjun Fan, Benyu Zhang, Yixin Chen
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
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
arXiv:2511. 04805v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input.
By Yushu Zhao, Zheng Wang, Minjia Zhang
arXiv:2503. 05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks.
By Justin Chih-Yao Chen, Sukwon Yun, Elias Stengel-Eskin, Tianlong Chen, Mohit Bansal
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.
arXiv:2609.25809v1 Announce Type: new
Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly man...
By Yuanteng Chen, Qiwei Lai, Chen Tianqi, Peisong Wang, Yuantian Shao, Nanxin Zeng, Zhilei Liu, Chuangyi Li, Jing Liu, Jian Cheng
arXiv:2606. 16825v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory.
By Martin Jaggi
ExFold is a training‑free expert‑folding framework that jointly accelerates the prefill and decode phases of Mixture‑of‑Experts (MoE) models by projecting the contributions of excluded experts onto a retained expert set using calibrated scalar projectors. It treats both phases as a budgeted output‑approximation problem, achieving token‑level Top‑K folding for prefill and batch‑level expert‑pool folding for decode. Implemented as a plug‑and‑play plugin in vLLM with a lightweight CUDA kernel, ExFold delivers up to 1.41× TTFT and 2.45× TPOT speedups while preserving about 99% of the original model quality.
By Juntong Wu, Yifei Liu, Junyi Chen, Siqi Fan, Chaoran Feng, Minghao Li, Liujie Zhang, Weihang Chen, Li Yuan