MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

• URL: http://arxiv.org/abs/2505.11415v2
• Date: Wed, 21 May 2025 13:20:21 GMT
• Title: MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
• Abstract summary: MoE architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently.<n>Existing benchmarks often fail to capture these trade-offs accurately.<n>We introduce MoE-CAP, a benchmark specifically designed for MoE systems.
• Score: 25.47183452671666
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy, and Performance (CAP), making trade-offs inevitable. Existing benchmarks often fail to capture these trade-offs accurately, complicating practical deployment decisions. To address this, we introduce MoE-CAP, a benchmark specifically designed for MoE systems. Our analysis reveals that achieving an optimal balance across CAP is difficult with current hardware; MoE systems typically optimize two of the three dimensions at the expense of the third-a dynamic we term the MoE-CAP trade-off. To visualize this, we propose the CAP Radar Diagram. We further introduce sparsity-aware performance metrics-Sparse Memory Bandwidth Utilization (S-MBU) and Sparse Model FLOPS Utilization (S-MFU)-to enable accurate performance benchmarking of MoE systems across diverse hardware platforms and deployment scenarios.

Related papers

• Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts [13.835014453826057]
  We develop MOSAIC, which formulates model architecture and systems co-design.<n>We instantiate the framework for sparse Mixture-of-Experts (MoE) language models.<n>We show that, within the calibrated sparsity range, an efficiency-agnostic model-FLOPs budget admits no interior optimal sparsity.
  arXiv  Detail & Related papers  (2026-08-11T07:49:00Z)
• Piper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism [1.0130502379786543]
  Training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale communication across heterogeneous networks, and severe workload imbalance.<n>We develop a mathematical model that quantifies memory, compute, and communication requirements for MoE configurations under various parallelization schemes.<n>We introduce Piper, a framework that leverages resource modeling to identify efficient training strategies for MoE models on target HPC platforms.
  arXiv  Detail & Related papers  (2026-05-06T15:47:14Z)
• SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding [3.1396754306335652]
  SpecMoE is a memory-efficient MoE inference system based on our self-assisted speculative decoding algorithm.<n>Our system improves inference throughput by up to $4.30times$, while significantly reducing bandwidth requirements of both memory and interconnect on memory-constrained systems.
  arXiv  Detail & Related papers  (2026-04-11T10:52:17Z)
• Empirical Recipes for Efficient and Compact Vision-Language Models [54.92440500651415]
  Vision-language models (VLMs) in resource-constrained settings demand low latency and high throughput.<n>We conduct an empirical end-to-end efficiency analysis and systematically profile inference to identify the dominant bottlenecks.<n>We develop optimization recipes tailored to compact VLMs that substantially reduce latency while preserving accuracy.
  arXiv  Detail & Related papers  (2026-03-17T17:17:40Z)
• ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling [56.88966608455977]
  ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters.<n>ZipMoE achieves up to $72.77%$ inference latency reduction and up to $6.76times$ higher throughput than the state-of-the-art systems.
  arXiv  Detail & Related papers  (2026-01-29T02:51:59Z)
• MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts [29.437264687850874]
  We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading.<n>MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens.<n>Our evaluation on memory-constrained devices shows that for the Phi-MoE model, MoE-SpeQ achieves at most 2.34x speedup over the state-of-the-art offloading framework.
  arXiv  Detail & Related papers  (2025-11-18T03:40:19Z)
• Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection [88.47928738482719]
  Linear State Space Models (SSMs) offer remarkable performance gains in sequence modeling.<n>Recent advances, such as Mamba, further enhance SSMs with input-dependent gating and hardware-aware implementations.<n>We introduce Routing Mamba (RoM), a novel approach that scales SSM parameters using sparse mixtures of linear projection experts.
  arXiv  Detail & Related papers  (2025-06-22T19:26:55Z)
• Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC [8.837470787975308]
  Large Language Models (LLMs) on edge devices offer significant privacy benefits.<n>These on-device LLMs inherently face performance limitations due to reduced model capacity and necessary compression techniques.<n>We introduce a systematic methodology -- encompassing model capability, development efficiency, and system resources -- for evaluating on-device LLMs.
  arXiv  Detail & Related papers  (2025-05-21T02:23:01Z)
• D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving [14.607254882119507]
  Combination of experts (MoE) model is a sparse variant of large language models (LLMs)<n>Despite its benefits, MoE is still too expensive to deploy on resource-constrained edge devices.<n>We propose D$2$MoE, an algorithm-system co-design framework that matches diverse task requirements by dynamically allocating the most proper bit-width to each expert.
  arXiv  Detail & Related papers  (2025-04-17T05:37:35Z)
• COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs [81.01082659623552]
  Large Language Models (LLMs) have demonstrated remarkable success across various domains.<n>Their optimization remains a significant challenge due to the complex and high-dimensional loss landscapes they inhabit.
  arXiv  Detail & Related papers  (2025-02-24T18:42:19Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems [26.493762260392284]
  MoE-CAP is a benchmarking method for evaluating sparse MoE systems.<n>Its key innovation is a sparsity-aware CAP analysis model, the first to integrate cost, performance, and accuracy metrics into a single diagram.
  arXiv  Detail & Related papers  (2024-12-10T00:19:28Z)
• GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environments [1.0558515062670693]
  Large language models (LLMs) in real-world scenarios remains a critical challenge.<n>These challenges often lead to inefficiencies in memory utilization, latency, and throughput.<n>We develop a framework to address these issues, achieving prediction errors between 9.9% and 42.3% for key metrics such as batch latency, TTFT, and decode throughput.
  arXiv  Detail & Related papers  (2024-12-06T05:46:43Z)
• HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
  We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency. HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
  arXiv  Detail & Related papers  (2024-11-03T04:25:46Z)
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• Can SAM Boost Video Super-Resolution? [78.29033914169025]
  We propose a simple yet effective module -- SAM-guidEd refinEment Module (SEEM) This light-weight plug-in module is specifically designed to leverage the attention mechanism for the generation of semantic-aware feature. We apply our SEEM to two representative methods, EDVR and BasicVSR, resulting in consistently improved performance with minimal implementation effort.
  arXiv  Detail & Related papers  (2023-05-11T02:02:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.