# Performance Characterization of Expert Router for Scalable LLM Inference

arXiv: https://arxiv.org/abs/2404.15153 · HTML: https://mlsanity.com/paper/2404.15153/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (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)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [Large Language Model Routing with Benchmark Datasets](https://mlsanity.com/paper/2309.15789/) (2023)
- [Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models](https://mlsanity.com/paper/2311.08692/) (2023)
- [Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning](https://mlsanity.com/paper/2310.03094/) (2023)
- [AutoMix: Automatically Mixing Language Models](https://mlsanity.com/paper/2310.12963/) (2023)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [Fine-Tuned Language Models Generate Stable Inorganic Materials as Text](https://mlsanity.com/paper/2402.04379/) (2024)
- [Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline](https://mlsanity.com/paper/2305.13144/) (2023)
- [Scaling Expert Language Models with Unsupervised Domain Discovery](https://mlsanity.com/paper/2303.14177/) (2023)
- [Pushing The Limit of LLM Capacity for Text Classification](https://mlsanity.com/paper/2402.07470/) (2024)
- [CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering](https://mlsanity.com/paper/2310.09536/) (2023)
- [Assured LLM-Based Software Engineering](https://mlsanity.com/paper/2402.04380/) (2024)

## Built on by (most cited first, 2 of 2)

- [Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems](https://mlsanity.com/paper/2502.00409/) (2025)
- [Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection](https://mlsanity.com/paper/2601.09692/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have experienced widespread adoption across scientific and industrial domains due to their versatility and utility for diverse tasks. Nevertheless, deploying and serving these models at scale with optimal throughput and latency remains a significant challenge, primarily because of LLMs' high computational and memory demands. Specialized models optimized for specific tasks can be combined through a routing mechanism to address these challenges, creating a modular inference system. This paper introduces Expert Router, a scalable routing architecture that directs prompts to specialized expert models. We characterize multiple Expert Router configurations, including different LLama 3 models with quantized and non-quantized weights under up to 1,000 concurrent users. Our findings reveal that Expert Router introduces minimal latency overhead, with the configuration of expert models being a dominating factor in performance outcomes. High-parameter expert models deliver stable throughput and latency under moderate concurrency levels. In contrast, smaller expert models maintain competitive performance across a wider range of concurrent users compared to tensor-parallelized baseline models. This highlights the potential of Expert Router for efficient and scalable LLM deployment.