arXiv:2501.10375v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory...
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.
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.
arXiv:2607. 19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes.
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.
arXiv:2606. 00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency.
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.
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: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.
The paper presents a budget‑aware compression pipeline for deploying 70B‑parameter language models on a single NVIDIA GPU. It examines how pruning, quantization, and KV‑cache compression interact, showing that layer‑wise pruning improves weight quantization robustness and that KV‑cache sparsification complements INT8 KV quantization without harming decoding speed. Using these insights, the authors compressed a 70B model to ~33 GB, achieving ~57 tokens/s on 10k‑token prompts on an A40 while maintaining accuracy within 5% on standard benchmarks.
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.