# Camel: Energy-Aware LLM Inference on Resource-Constrained Devices

arXiv: https://arxiv.org/abs/2508.09173 · HTML: https://mlsanity.com/paper/2508.09173/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2025.

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

- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [Semantic Context Matters: Improving Conditioning for Autoregressive Models](https://mlsanity.com/paper/2511.14063/) (2025)
- [Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation](https://mlsanity.com/paper/2601.00322/) (2026)
- [HealthSLM-Bench: Benchmarking Small Language Models for Mobile and Wearable Healthcare Monitoring](https://mlsanity.com/paper/2509.07260/) (2025)
- [Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks](https://mlsanity.com/paper/2511.05598/) (2025)
- [SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2509.18593/) (2025)
- [Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking](https://mlsanity.com/paper/2602.20680/) (2026)
- [Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offs](https://mlsanity.com/paper/2603.29736/) (2026)
- [Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices](https://mlsanity.com/paper/2607.05933/) (2026)
- [DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining](https://mlsanity.com/paper/2510.06746/) (2025)
- [When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editing](https://mlsanity.com/paper/2603.04696/) (2026)
- [Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking](https://mlsanity.com/paper/2603.12949/) (2026)
- [ReconMIL: Synergizing Latent Space Reconstruction with Bi-Stream Mamba for Whole Slide Image Analysis](https://mlsanity.com/paper/2603.19925/) (2026)
- [FrugalSOT - Frugal Search Over the Models](https://mlsanity.com/paper/2608.21621/) (2026)

## Abstract (arXiv)

Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as network latency, privacy concerns, and bandwidth limits. Thus, deploying LLMs on edge devices has become an important research focus. In edge inference, request latency is critical as high latency can impair real-time tasks. At the same time, edge devices usually have limited battery capacity, making energy consumption another major concern. Balancing energy consumption and inference latency is essential. To address this, we propose an LLM inference energy management framework that optimizes GPU frequency and batch size to balance latency and energy consumption. By effectively managing the exploration-exploitation dilemma in configuration search, the framework finds the optimal settings. The framework was implemented on the NVIDIA Jetson AGX Orin platform, and a series of experimental validations were conducted. Results demonstrate that, compared to the default configuration, our framework reduces energy delay product (EDP) by 12.4%-29.9%, achieving a better balance between energy consumption and latency.