arXiv:2608. 02989v1 Announce Type: new Abstract: Speculative decoding verifies a tree of draft tokens in one target-model forward pass.
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.
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...
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:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.
arXiv:2608. 08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs.
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.
MetaNet is a support‑set controller that predicts, for each layer of a Mixture‑of‑Experts model, an expert‑retention threshold and a bounded routing bias while keeping the backbone, experts, and router frozen. On DeepSeek‑MoE‑16B‑Chat, MetaNet offers a tunable trade‑off between accuracy and expert activation: a conservative setting activates 3.61 experts on average (40% fewer than a fixed k=6) with comparable MMLU accuracy, whereas an aggressive setting activates only 2.28 experts (62% fewer) with a modest accuracy drop. The MMLU‑trained controller also transfers to C‑Eval, activating 2.90 experts on average (52% fewer than fixed k=6) at 0.386 accuracy.
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.
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: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).
The paper introduces a cache‑aware post‑training framework for Mixture‑of‑Experts (MoE) models that jointly adapts the MoE backbone and lightweight auxiliary cache routers while keeping the native Top‑K expert‑selection rule. Two modes are proposed: Temporal Router, which predicts same‑layer reuse and retains experts for future tokens, and Spatio‑Temporal Router, which adds a Spatio Router that refines the temporal cache using the causal predecessor’s hidden state. Experiments on Qwen3 and GPT‑OSS across GSM8K, MATH, and CommonsenseQA show that Temporal Router improves cache hit rates and reduces expert‑weight traffic, while Spatio‑Temporal Router achieves the best load‑adjusted efficiency, outperforming strong prefetching baselines.
Dynamic Expert Quantization (DynaExq) is a runtime-aware mixed-precision serving system designed for single‑GPU Mixture‑of‑Experts (MoE) inference under a hard high‑bandwidth memory (HBM) envelope. It treats the problem as an online, budget‑constrained precision allocation task, keeping the most frequently used experts at higher precision while relegating the rest to low‑precision fallbacks. By estimating expert hotness from router traces and asynchronously promoting or demoting experts, DynaExq maintains a fully materialized expert set during the forward pass, improving accuracy and throughput compared to static post‑training quantization and offloading/prefetch baselines. whyItMatters":"DynaExq enables efficient deployment of large MoE models on memory‑limited GPUs by dynamically allocating precision based on runtime expert usage, thereby reducing memory footprint and latency while boosting accuracy and throughput."