pith. sign in

arxiv: 2506.19884 · v1 · pith:I56OC7JBnew · submitted 2025-06-24 · 💻 cs.OS · cs.AI· cs.PF· cs.SE

MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection

classification 💻 cs.OS cs.AIcs.PFcs.SE
keywords energymnn-aecsdevicesdecodingadaptivecoredecodeenergy-efficient
0
0 comments X
read the original abstract

As the demand for on-device Large Language Model (LLM) inference grows, energy efficiency has become a major concern, especially for battery-limited mobile devices. Our analysis shows that the memory-bound LLM decode phase dominates energy use, and yet most existing works focus on accelerating the prefill phase, neglecting energy concerns. We introduce Adaptive Energy-Centric Core Selection (AECS) and integrate it into MNN to create the energy-efficient version, MNN-AECS, the first engine-level system solution without requiring root access or OS modifications for energy-efficient LLM decoding. MNN-AECS is designed to reduce LLM decoding energy while keeping decode speed within an acceptable slowdown threshold by dynamically selecting low-power CPU cores. MNN-AECS is evaluated across 5 Android and 2 iOS devices on 5 popular LLMs of various sizes. Compared to original MNN, MNN-AECS cuts down energy use by 23% without slowdown averaged over all 7 devices and 4 datasets. Against other engines, including llama.cpp, executorch, mllm, and MediaPipe, MNN-AECS delivers 39% to 78% energy saving and 12% to 363% speedup on average.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.