# BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization

arXiv: https://arxiv.org/abs/2602.10729 · HTML: https://mlsanity.com/paper/2602.10729/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 40 of its 58 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 30 of 40)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [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)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [High Dimensional Bayesian Optimisation and Bandits via Additive Models](https://mlsanity.com/paper/1503.01673/) (2015)
- [Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement](https://mlsanity.com/paper/2105.08195/) (2021)
- [Structure Discovery in Nonparametric Regression through Compositional Kernel Search](https://mlsanity.com/paper/1302.4922/) (2013)
- [Decentralized Training of Foundation Models in Heterogeneous Environments](https://mlsanity.com/paper/2206.01288/) (2022)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention](https://mlsanity.com/paper/2509.24006/) (2025)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism](https://mlsanity.com/paper/2211.13878/) (2022)
- [TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times](https://mlsanity.com/paper/2512.16093/) (2025)
- [HexGen: Generative Inference of Large Language Model over Heterogeneous Environment](https://mlsanity.com/paper/2311.11514/) (2023)
- [Adaptive LLM Routing under Budget Constraints](https://mlsanity.com/paper/2508.21141/) (2025)
- [ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments](https://mlsanity.com/paper/2502.09334/) (2025)
- [Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs](https://mlsanity.com/paper/2502.00722/) (2025)
- [SkyServe: Serving AI Models across Regions and Clouds with Spot Instances](https://mlsanity.com/paper/2411.01438/) (2024)

## Built on by (most cited first, 6 of 6)

- [OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration](https://mlsanity.com/paper/2602.12151/) (2026)
- [Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs](https://mlsanity.com/paper/2605.04357/) (2026)
- [Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics](https://mlsanity.com/paper/2604.07144/) (2026)
- [HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling](https://mlsanity.com/paper/2605.16637/) (2026)
- [TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving](https://mlsanity.com/paper/2608.18149/) (2026)
- [OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving](https://mlsanity.com/paper/2609.14237/) (2026)

## Abstract (arXiv)

The rapid growth of large language model (LLM) deployments has made cost-efficient serving systems essential. Recent efforts to enhance system cost-efficiency adopt two main perspectives: (i) An algorithmic perspective that exploits heterogeneous model capabilities to route simpler queries to lower-cost models and complex queries to higher-cost models (i.e., heterogeneous query routing); and (ii) a systems perspective that utilizes heterogeneous GPU resources as cost-effective alternatives to homogeneous high-end GPUs (i.e., heterogeneous model deployment). However, algorithm-system co-design for cost-efficient LLM serving necessitates sophisticated management: (i) Determining optimal query routing strategies under latency and quality requirements, (ii) configuring model deployment across heterogeneous GPUs with appropriate resource allocation and parallelism strategies, and (iii) co-optimizing routing and deployment decisions to maximize overall system performance. To address these challenges, we present BOute, a quality-aware scheduling system that jointly exploits heterogeneous model and GPU capabilities for cost-efficient LLM serving. BOute employs a multi-objective Bayesian optimization (MOBO) framework to co-optimize the routing strategy and model deployment, thereby maximizing the cost-efficiency of the serving system while guaranteeing response quality. Evaluation results demonstrate that BOute outperforms state-of-the-art LLM serving systems by up to 157% and 59% on average under identical cost budgets and quality requirements, or reducing serving costs by 15%-61% (38% on average) while maintaining the same performance targets, validating its effectiveness in achieving cost-efficient LLM serving.