ACL Findings2026
EOP-LLM: Energy Oriented Pruning for Large Language Models
Guan Huang, Tao Shu
Abstract
In deployed large language models (LLMs), inference energy consumption has grown rapidly and has emerged as a key bottleneck in largescale deployment, yet most existing inference efficiency methods focus on reducing FLOPs or latency, rather than explicitly modeling or enforcing end-to-end inference energy constraints. We propose EOP-LLM, an energy-oriented dynamic pruning framework that enables LLM inference under explicit per-sequence energy budgets. EOP-LLM combines a device-calibrated energy proxy with lightweight token and feedforward (FFN) selectors, coordinated through a global dual variable, to dynamically allocate computation while preserving model quality. Extensive experiments on LLaMA 3.2 (1B/3B) and LLaMA 3.1 (8B) demonstrate that EOP-LLM consistently outperforms state-of-the-art dynamic pruning baselines under matched energy budgets, while strictly adhering to persequence energy constraints.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness cites Compressive Transformers for Long-Range Sequence Modelling
- Efficient Memory Management for Large Language Model Serving with PagedAttention cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Builds on21
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra et al.NeurIPS 2022 · 5,493 citations
- PIQA: Reasoning about Physical Commonsense in Natural LanguageYonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao et al.AAAI 2020 · 2,916 citations
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language ModelsGuangxuan Xiao, Ji Lin, Mickaël Seznec, Hao Wu et al.ICML 2023 · 1,493 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- Compressive Transformers for Long-Range Sequence ModellingJack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, Chloe Hillier et al.ICLR 2020 · 833 citations
Related papers
- TokenPowerBench: Benchmarking the Power Consumption of LLM InferenceChenxu Niu, Wei Zhang, Jie Li, Yongjian Zhao et al.AAAI 2026 · 12 citations
- OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMsYang Ji, Ying SunACL 2026
- Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-ProbingQi Le, Enmao Diao, Ziyan Wang, Xinran Wang et al.ICLR 2025
- Bring Future Vision: Dynamic Computation Allocation Guided by Lightweight Feature ForecasterChao Han, Yijuan Liang, Zihao Xuan, Daokuan Wu et al.ICML 2026
- DynamoLLM: Designing LLM Inference Clusters for Performance and Energy EfficiencyJovan Stojkovic, Chaojie Zhang, Íñigo Goiri, Josep Torrellas et al.HPCA 2025 · 106 citations
