cs.LGFeb 12, 2026

MUSE: Multi-Tenant Model Serving With Seamless Model Updates

Authors: Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins, Miguel P. Bento, Sofia Guerreiro, Ricardo Ribeiro Pereira, Ana Sofia Gomes, Jacopo Bono, 

Organizations: Feedzai Portugal

Abstract

In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model scores but also on the specific business decisions of each client using that model. However, retraining models inevitably shifts score distributions, invalidating existing thresholds. In multi-tenant Score-as-a-Service environments, where decision boundaries reside in client-managed infrastructure, this creates a severe bottleneck: recalibration requires coordinating threshold updates across hundreds of clients, consuming excessive human hours and leading to model stagnation. We introduce MUSE, a model serving framework that enables seamless model updates by decoupling model scores from client decision boundaries. Designed for multi-tenancy, MUSE optimizes infrastructure re-use by sharing models via dynamic intent-based routing, combined with a two-level score transformation that maps model outputs to a stable, reference distribution. Deployed at scale by Feedzai, MUSE processes over a thousand events per second, and over 55 billion events in the last 12 months, across several dozens of tenants, while maintaining high-availability and low-latency guarantees. By reducing model lead time from weeks to minutes, MUSE promotes model resilience against shifting attacks, saving millions of dollars in fraud losses and operational costs.

Figures & tables

Explore similar work

CardsList
  1. FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving

    Apr 29, 2026Minghe Wang, Trever Schirmer, Mohammadreza Malekabbasi +1Mixture-of-Experts Language ModelsLLM Serving

  2. JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

    Jul 17, 2026Haoran Sun, Wentao Zhang, Junyang Hua +18Efficient VLA Model InferenceVLA Model Post-Training

  3. Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models

    Mar 12, 2026Jae-Won Chung, Jeff J. Ma, Jisang Ahn +4LLM Inference Serving