← Back to all news
arXiv Machine Learning By Molka Chkir, Syed Muhammad Danish, Jos H\"oll, Arghavan Asad

Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures

Read the original on arXiv Machine Learning →

The paper systematically studies decode‑phase energy consumption of open‑source large language models using different attention architectures—Multi‑Head Attention (MHA), Grouped Query Attention (GQA), and GQA with Sliding Window Attention (SWA). It evaluates four models across varying context lengths, batch sizes, and generation workloads, measuring GPU energy via NVIDIA counters. Findings show that the attention mechanism is the main driver of how energy scales with context length, with MHA models growing steeply, GQA models growing less, and GQA+SWA remaining nearly constant; model size mainly sets absolute energy use, while batching can cut energy per token and latency by up to 87%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 21

Attentions Under the Microscope: A Comparative Study of Resource Utilization for Variants of Self-Attention

arXiv:2507. 07247v2 Announce Type: replace-cross Abstract: As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity.

By Zhengyu Tian, Anantha Padmanaban Krishna Kumar, Hemant Krishnakumar, Reza Rawassizadeh
llmsefficiencybenchmarks
More like this →
Hugging Face Trending Papers
Jul 29

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems. However, direct measurement of inference energy often requires hardware telemetry, power instrumentation, or infrastructure-specific monitoring, limiting its applicability in comparative studies, early-stage system design, and sustainability reporting.

llms
More like this →
arXiv Machine Learning
Jul 30

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

arXiv:2607. 26571v1 Announce Type: new Abstract: The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems.

By Tina Vartziotis, Rodopi Kosteli, Elli Vartziotis, George Dasoulas, Michael Keckeisen, Konstantinos Skianis, Sotirios Kotsopoulos, Francesca Dominici
llms
More like this →
arXiv AI
Sep 28

Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer Hardware

The paper reports a reproducible GPU power benchmark for 18 open‑source LLMs (0.5B–7B parameters) run on a single consumer RTX 4060ti GPU using the Ollama inference engine. Energy metrics such as mean/peak power, total energy per prompt, energy per output token, and throughput were measured, revealing that model architecture and quantization strategy, rather than parameter count alone, drive energy efficiency. The most efficient models were qwen2.5:0.5b and tinyllama:1.1b, while the 7B‑Mistral model consumed up to 8.6× more energy per token, and qwen3.5:0.8b(on) showed unusually high per‑prompt energy due to extended internal reasoning.

By Philipp M. Z\"ahl, Elja Dalipaj, Anika Hennig, Timon Bayer
llmsefficiencybenchmarkssafety
More like this →