paper-with-me

Papers

Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference

2023-03-10 · Haiyang Huang, Newsha Ardalani, Anna Sun, Liu Ke, Hsien-Hsin S. Lee, Anjali Sridhar, Shruti Bhosale, Carole-Jean Wu, Benjamin Lee

Mixture-of-Experts (MoE) models have gained popularity in achieving state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity while incurring a minimal increase in computation cost during training. However, deploying such models for inference is difficult due to their large size and complex communication pattern. In this work, we provide a characterization of two MoE workloads, namely Language Modeling (LM) and Machine Translation (MT) and identify their sources of inefficiencies at deployment. We propose three optimization techniques to mitigate sources of inefficiencies, namely (1) Dynamic gating, (2) Expert Buffering, and (3) Expert load balancing. We show that dynamic gating improves maximum throughput by 6.21-11.23$\times$ for LM, 5.75-10.98$\times$ for MT Encoder and 2.58-5.71$\times$ for MT Decoder. It also reduces memory usage by up to 1.36$\times$ for LM and up to 1.1$\times$ for MT. We further propose Expert Buffering, a new caching mechanism that only keeps hot, active experts in GPU memory while buffering the rest in CPU memory. This reduces static memory allocation by up to 1.47$\times$. We finally propose a load balancing methodology that provides additional scalability to the workload.

📄 PDF Abstract BibTeX arXiv:2303.06182

Code (0)

등록된 구현이 없습니다.

Tasks

CPUDecoderGPULanguage ModelingLanguage ModellingMachine TranslationMixture-of-Experts

Similar Papers 제목 키워드 기반

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts

2025-03-07 · Shwai He, Weilin Cai, Jiayi Huang, Ang Li

The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation, optimizing the trade-off between performance and efficiency. However, under expert paral…

Mixture-of-Experts

CoX-MoE: Coalesced Expert Execution for High-Throughput MoE Inference with AMX-Enabled CPU-GPU Co-Execution

2026-05-18 · Muyoung Son, Yi Chen, Seungjae Yoo, Soongyu Choi 외 arxiv

The Mixture-of-Experts (MoE) architecture improves computational efficiency via sparse expert activation, but throughput-oriented inference faces substantial GPU memory pressure due to a significant parameter size and in…

Computational Efficiency

Optimizing Distributed Deployment of Mixture-of-Experts Model Inference in Serverless Computing

2025-01-09 · Mengfan Liu, Wei Wang, Chuan Wu

With the advancement of serverless computing, running machine learning (ML) inference services over a serverless platform has been advocated, given its labor-free scalability and cost effectiveness. Mixture-of-Experts (M…

Bayesian OptimizationCPUMixture-of-Experts

Mixture of Lookup Experts

2025-03-20 · Shibo Jie, Yehui Tang, Kai Han, Yitong Li 외

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up. However, since MoE dynamically selects t…

Mixture-of-Experts

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

2025-09-24 · Sampurna Roy, Ayan Sar, Anurag Kaushish, Kanav Gupta 외 arxiv

Contemporary transformer architectures apply identical processing depth to all inputs, creating inefficiencies and limiting reasoning quality. Simple factual queries are subjected to the same multilayered computation as …