# LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services

arXiv: https://arxiv.org/abs/2410.02425 · HTML: https://mlsanity.com/paper/2410.02425/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 69 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [CodeGen2: Lessons for Training LLMs on Programming and Natural Languages](https://mlsanity.com/paper/2305.02309/) (2023)
- [Predicting the Computational Cost of Deep Learning Models](https://mlsanity.com/paper/1811.11880/) (2018)
- [How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench](https://mlsanity.com/paper/2305.14947/) (2023)
- [LLM Performance Predictors are good initializers for Architecture Search](https://mlsanity.com/paper/2310.16712/) (2023)
- [Toward Accurate Platform-Aware Performance Modeling for Deep Neural Networks](https://mlsanity.com/paper/2012.00211/) (2020)

## Built on by (most cited first, 14 of 14)

- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving](https://mlsanity.com/paper/2411.17651/) (2024)
- [Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective](https://mlsanity.com/paper/2508.16712/) (2025)
- [Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study](https://mlsanity.com/paper/2505.02502/) (2025)
- [Governing Cloud Data Pipelines with Agentic AI](https://mlsanity.com/paper/2512.23737/) (2025)
- [From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap](https://mlsanity.com/paper/2410.20791/) (2024)
- [Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model](https://mlsanity.com/paper/2602.07878/) (2026)
- [ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction](https://mlsanity.com/paper/2503.20978/) (2025)
- [Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters](https://mlsanity.com/paper/2602.17697/) (2026)
- [Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference](https://mlsanity.com/paper/2606.02430/) (2026)
- [Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations](https://mlsanity.com/paper/2607.09172/) (2026)
- [Software Performance Engineering for Foundation Model-Powered Software](https://mlsanity.com/paper/2411.09580/) (2024)
- [The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)](https://mlsanity.com/paper/2505.10640/) (2025)
- [Think Before You Grid-Search: Floor-First Triage for LLM Serving](https://mlsanity.com/paper/2607.05876/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) are rapidly growing in popularity, LLM inference services must be able to serve requests from thousands of users while satisfying performance requirements. The performance of an LLM inference service is largely determined by the hardware onto which it is deployed, but understanding of which hardware will deliver on performance requirements remains challenging. In this work we present LLM-Pilot - a first-of-its-kind system for characterizing and predicting performance of LLM inference services. LLM-Pilot performs benchmarking of LLM inference services, under a realistic workload, across a variety of GPUs, and optimizes the service configuration for each considered GPU to maximize performance. Finally, using this characterization data, LLM-Pilot learns a predictive model, which can be used to recommend the most cost-effective hardware for a previously unseen LLM. Compared to existing methods, LLM-Pilot can deliver on performance requirements 33% more frequently, whilst reducing costs by 60% on average.