arXiv:2607. 24434v1 Announce Type: cross Abstract: 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.
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.
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.
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.
arXiv:2608. 02989v1 Announce Type: new Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass.
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.
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...
arXiv:2608. 15383v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving the full expert bank.
arXiv:2607. 24787v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory.
ACE introduces a training‑free, calibration‑free framework for adaptive expert skipping in Mixture‑of‑Experts LLMs. It combines a Global Spectral Proxy that estimates global transformation capacity with a Router‑Conditioned Refinement that builds expert‑specific direction prototypes, enabling the model to skip low‑contribution experts while always keeping the top‑1 expert. Offline computation of expert statistics leaves only lightweight table lookups during inference, and experiments on three MoE‑based LLMs show ACE outperforms static and dynamic baselines, especially at high skipping ratios.
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
FluxMoE introduces an expert paging system that decouples Mixture-of-Experts (MoE) model experts from permanent GPU residency, allowing dynamic adaptation to available memory. By combining PagedTensor, a bandwidth‑balanced memory hierarchy, and a budget‑aware residency planner, FluxMoE streams expert weights on demand while keeping computations on GPUs. Experiments on GLM‑4.5 and Mixtral‑8×7B‑Instruct show significant throughput gains and reduced time‑per‑output‑token compared to existing inference engines, without compromising model quality.