# Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations

arXiv: https://arxiv.org/abs/2607.09172 · HTML: https://mlsanity.com/paper/2607.09172/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 63 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 30 of 34)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [A Thorough Examination of Decoding Methods in the Era of LLMs](https://mlsanity.com/paper/2402.06925/) (2024)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference](https://mlsanity.com/paper/2403.20306/) (2024)
- [Energy Considerations of Large Language Model Inference and Efficiency Optimizations](https://mlsanity.com/paper/2504.17674/) (2025)
- [LLM Inference Serving: Survey of Recent Advances and Opportunities](https://mlsanity.com/paper/2407.12391/) (2024)
- [Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM](https://mlsanity.com/paper/2403.19114/) (2024)
- [Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency](https://mlsanity.com/paper/2504.03360/) (2025)
- [Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems](https://mlsanity.com/paper/2407.04014/) (2024)
- [Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation](https://mlsanity.com/paper/2410.06097/) (2024)
- [Guidelines for Empirical Studies in Software Engineering involving Large Language Models](https://mlsanity.com/paper/2508.15503/) (2025)
- [LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences](https://mlsanity.com/paper/2410.02950/) (2024)
- [Seesaw: High-throughput LLM Inference via Model Re-sharding](https://mlsanity.com/paper/2503.06433/) (2025)
- [LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services](https://mlsanity.com/paper/2410.02425/) (2024)
- [Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter](https://mlsanity.com/paper/2511.16665/) (2025)
- [A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency](https://mlsanity.com/paper/2505.01658/) (2025)
- [On the Suitability of Hugging Face Hub for Empirical Studies](https://mlsanity.com/paper/2307.14841/) (2023)
- [Green My LLM: Studying the key factors affecting the energy consumption of code assistants](https://mlsanity.com/paper/2411.11892/) (2024)
- [The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines](https://mlsanity.com/paper/2408.01050/) (2024)
- [Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use](https://mlsanity.com/paper/2601.22362/) (2026)

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

- [P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM Serving](https://mlsanity.com/paper/2608.15171/) (2026)

## Abstract (arXiv)

Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this paper, we present a large-scale controlled study of three selected vLLM configuration options: attention kernel type, prefix caching, and chunked prefill. We evaluate all combinations of these configurations across 5 open-weight LLMs and 5 diverse inference tasks, totaling 9,000 runs and 93,600 measures. We analyze energy consumption, latency, and accuracy, and examine both main effects and interaction effects between configuration options and tasks. Our results show that the studied configuration options significantly impact energy and performance, mainly driven by attention type and prefix caching, while chunked prefill has a limited effect under the default vLLM serving configuration and evaluated workloads. These effects are highly model- and workload-dependent, and no configuration is universally optimal. We further show that model choice dominates global trade-offs, while configuration tuning provides local improvements along the Pareto frontier. Unexpectedly, inference options can also affect model accuracy.