arXiv:2607. 08782v1 Announce Type: cross Abstract: Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models.
arXiv:2606. 01007v1 Announce Type: cross Abstract: Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert communication and routing-induced load imbalance.
arXiv:2608. 14205v1 Announce Type: new Abstract: Load imbalance poses a major bottleneck to the efficiency of expert parallelism in distributed inference of Mixture-of-Experts (MoE) models.
arXiv:2608. 07964v1 Announce Type: cross Abstract: Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models.
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."
arXiv:2603.06350v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constrai...
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...
arXiv:2609.00407v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models enable efficient scaling of large language model (LLM) inference but suffer from substantial data-movement overhead w...
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:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
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).
arXiv:2607. 11586v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded.
arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.