# LMEdge: QoS-Aware LLM Inference Orchestration on Edge Clusters

arXiv: https://arxiv.org/abs/2607.17175 · HTML: https://mlsanity.com/paper/2607.17175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference](https://mlsanity.com/paper/2404.07947/) (2024)
- [Cost-Effective Online Multi-LLM Selection with Versatile Reward Models](https://mlsanity.com/paper/2405.16587/) (2024)
- [OptLLM: Optimal Assignment of Queries to Large Language Models](https://mlsanity.com/paper/2405.15130/) (2024)
- [Edge-First Language Model Inference: Models, Metrics, and Tradeoffs](https://mlsanity.com/paper/2505.16508/) (2025)
- [Serving Long-Context LLMs at the Mobile Edge: Test-Time Reinforcement Learning-based Model Caching and Inference Offloading](https://mlsanity.com/paper/2501.14205/) (2025)

## Built on by (most cited first, 1 of 1)

- [DRLM: Deep Reinforcement Learning-Based LLM Query Orchestration in Edge Environments](https://mlsanity.com/paper/2609.00442/) (2026)

## Abstract (arXiv)

Large language model (LLM) services increasingly operate on edge infrastructure, enabling low-latency and privacy-preserving AI services. However, efficiently serving LLM requests across heterogeneous and resource-constrained edge devices require orchestration mechanisms that jointly determine model configuration (family, size, and quantization level) and execution placement while satisfying user- and system-level quality of service (QoS) requirements. This paper introduces LMEdge, a QoS-aware orchestration service that dynamically makes these decisions across heterogeneous edge devices. We formulate the problem as a binary integer linear programming (BILP) optimization that minimizes response time under accuracy, network, and resource constraints. To enable scalable online scheduling, we employ five lightweight machine learning (ML) models to predict query-specific latency, accuracy, resource usage, and response size for each model-size-quantization-device combination, and design a lightweight heuristic that approximates the BILP solution. We collect a comprehensive benchmarking dataset of over 59000 rows to train models and support reproducibility. Evaluation on a Kubernetes-based edge testbed with 57 instances and diverse query categories shows that LMEdge reduces latency, preserves accuracy, improves resource utilization, and increases serving ratio compared to two baselines.