paper-with-me

Papers

ProMoE: Fast MoE-based LLM Serving using Proactive Caching

2024-10-29 · Xiaoniu Song, Zihang Zhong, Rong Chen, Haibo Chen

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's parameters during computation. This approach allows the unused parameters to be offloaded to host memory, thereby reducing the overall GPU memory demand. However, existing cache-based offloading solutions handle cache misses reactively, which significantly impacts system performance. In this paper, we introduce ProMoE, a novel proactive caching system that utilizes intermediate results to predict subsequent expert usage. By proactively fetching experts in advance, ProMoE eliminates passive cache misses, removes loading time from the critical path, and reduces the performance overhead associated with offloading. Our evaluations demonstrate that ProMoE achieves an average speedup of 2.20x (up to 3.21x) and 2.07x (up to 5.02x) in the prefill and decode stages, respectively, compared to existing offloading solutions.

📄 PDF Abstract BibTeX arXiv:2410.22134

Code (0)

등록된 구현이 없습니다.

Tasks

GPUMixture-of-Experts

Similar Papers 제목 키워드 기반

Graph Federated Learning Based Proactive Content Caching in Edge Computing

2025-02-07 · Rui Wang

With the rapid growth of mobile data traffic and the increasing prevalence of video streaming, proactive content caching in edge computing has become crucial for reducing latency and alleviating network congestion. Howev…

Edge-computingFederated Learning

Context-Aware Proactive Content Caching with Service Differentiation in Wireless Networks

2016-06-14 · Sabrina Müller, Onur Atan, Mihaela van der Schaar, Anja Klein

Content caching in small base stations or wireless infostations is considered to be a suitable approach to improve the efficiency in wireless content delivery. Placing the optimal content into local caches is crucial due…

ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities

2026-07-07 · Aavash Chhetri, Bibek Niroula, Eduard Vazquez, Yash Raj Shrestha 외 arxiv

In this paper, we address the problem of multimodal federated learning with missing modality. Existing methods utilize an additional public dataset or perform naive feature synthesis that is based solely on the available…

Federated Learning

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance

2025-10-28 · Yujie Wei, Shiwei Zhang, Hangjie Yuan, Yujin Han 외 arxiv

Mixture-of-Experts (MoE) has emerged as a powerful paradigm for scaling model capacity while preserving computational efficiency. Despite its notable success in large language models (LLMs), existing attempts to apply Mo…

Computational Efficiency

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

2025-04-19 · Hang Zhang, Jiuchen Shi, Yixiao Wang, Quan Chen 외

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accel…

Language ModelingLanguage ModellingLarge Language ModelManagement