paper-with-me

홈 › Papers

Ensuring Fair LLM Serving Amid Diverse Applications

2024-11-24 · Redwan Ibne Seraj Khan, Kunal Jain, Haiying Shen, Ankur Mallick, Anjaly Parayil, Anoop Kulkarni, Steve Kofsky, Pankhuri Choudhary, Renèe St. Amant, Rujia Wang, Yue Cheng, Ali R. Butt, Victor Rühle, Chetan Bansal, Saravan Rajmohan

In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness. Existing fairness approaches do not account for variations in token lengths across applications and multiple LLM calls, making them unsuitable for such platforms. To address the fairness challenge, this paper analyzes millions of requests from thousands of users on MS CoPilot, a real-world multi-tenant LLM platform hosted by Microsoft. Our analysis confirms the inadequacy of existing methods and guides the development of FairServe, a system that ensures fair LLM access across diverse applications. FairServe proposes application-characteristic aware request throttling coupled with a weighted service counter based scheduling technique to curb abusive behavior and ensure fairness. Our experimental results on real-world traces demonstrate FairServe's superior performance compared to the state-of-the-art method in ensuring fairness. We are actively working on deploying our system in production, expecting to benefit millions of customers world-wide.

📄 PDF Abstract BibTeX arXiv:2411.15997

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessLanguage ModelingLanguage ModellingLarge Language ModelScheduling

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Locality-aware Fair Scheduling in LLM Serving

2025-01-24 · Shiyi Cao, Yichuan Wang, Ziming Mao, Pin-Lun Hsu 외

Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing dive…

FairnessLanguage ModelingLanguage ModellingLarge Language Model+1

FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA

2025-07-21 · Minghan Li, Congcong Wen, Yu Tian, Min Shi 외 arxiv

Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presents a collaborative and privacy-preservin…

Medical Image ClassificationFederated Learning

Expert-Like Reparameterization of Heterogeneous Pyramid Receptive Fields in Efficient CNNs for Fair Medical Image Classification

2025-05-19 · Xiao Wu, Xiaoqing Zhang, Zunjie Xiao, Lingxi Hu 외

Efficient convolutional neural network (CNN) architecture designs have attracted growing research interests. However, they usually apply single receptive field (RF), small asymmetric RFs, or pyramid RFs to learn differen…

Fairnessimage-classificationImage ClassificationMedical Diagnosis+1

Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI

2025-03-20 · Dawood Wasif, Dian Chen, Sindhuja Madabushi, Nithin Alluru 외

Federated Learning (FL) enables collaborative machine learning while preserving data privacy but struggles to balance privacy preservation (PP) and fairness. Techniques like Differential Privacy (DP), Homomorphic Encrypt…

BenchmarkingFairnessFederated Learning

FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction

2024-10-07 · Siqi Li, Qiming Wu, Xin Li, Di Miao 외

Objective: Mitigating algorithmic disparities is a critical challenge in healthcare research, where ensuring equity and fairness is paramount. While large-scale healthcare data exist across multiple institutions, cross-i…

FairnessFederated LearningPrivacy Preserving