# Load Testing for Machine Learning Model Serving Systems at Scale

arXiv: https://arxiv.org/abs/2606.22013 · HTML: https://mlsanity.com/paper/2606.22013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [The Architectural Implications of Facebook's DNN-based Personalized Recommendation](https://mlsanity.com/paper/1906.03109/) (2019)
- [AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving](https://mlsanity.com/paper/2302.11665/) (2023)
- [A Runtime-Based Computational Performance Predictor for Deep Neural Network Training](https://mlsanity.com/paper/2102.00527/) (2021)

## Abstract (arXiv)

Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc. Under-provisioning leads to service-level objective (SLO) violations and production incidents, while over-provisioning results in substantial resource waste. This paper presents sys, an industrial load testing framework for ML serving systems that systematically estimates serving capacity through an adaptive, feedback-driven search strategy. The approach leverages real-time performance signals, incorporating dampening, spike tolerance, and convergence detection to efficiently identify maximum sustainable throughput under SLO constraints. We evaluate sys through a longitudinal analysis of 14 industrial case studies spanning four ML architecture classes: recommendation, ranking, vision, and NLP. This study demonstrates that systematic load testing leads to substantial improvements in GPU resource efficiency and operational reliability. Prior to adopting sys, a significant fraction of model launches were under-provisioned, resulting in recurring incidents; these issues were substantially reduced after deployment. Our results show that ML-specific design decisions are critical to accurate capacity estimation: workload calibration using recorded traffic reduces estimation error from approximately 30% to 2--6%, while proper warmup handling yields a 22.2% improvement in accuracy. Further analysis reveals key factors influencing prediction error, including model size and co-location effects. This paper distills six lessons and derive architectural guidelines for ML load testing, offering actionable insights for building reliable and efficient ML serving systems.