Related papers: Analyzing the Resource Utilization of Lambda Funct…
Source code is usually formatted with elements like indentation and newlines to improve readability for human developers. However, these visual aids do not seem to be beneficial for large language models (LLMs) in the same way since the…
Context information brings new opportunities for efficient and effective applications and services on mobile devices. A wide range of research has exploited context dependency, i.e., the relations between context(s) and the outcome, to…
Context. Nowadays, 83% of software developers use Large Language Models (LLMs) to generate code. LLMs recently became essential to increase the productivity of software developers and decrease the time and cost of software development.…
During the last years, many improvements were made to the hardware capability of mobile devices. As mobile software also became more interactive and data processing intensive, the increased power demand could not be compensated by the…
While small language models (SLMs) show promises for mobile deployment, their real-world performance and applications on smartphones remains underexplored. We present SlimLM, a series of SLMs optimized for document assistance tasks on…
This paper provides both theoretical and experimental evidence for the existence of an Energy/Frequency Convexity Rule, which relates energy consumption and CPU frequency on mobile devices. We monitored a typical smartphone running a…
Mobile devices, like sensor networks and MEMS actuators use mobile power supplies to ensure energy for their operation. These are mostly batteries. The lifetime of the devices depends on the power consumption and on the quality and…
Large Language Models (LLMs) are increasingly being integrated into various applications and services running on billions of mobile devices. However, deploying LLMs on resource-limited mobile devices faces a significant challenge due to…
Context. Many Internet content platforms, such as Spotify and YouTube, provide their services via both native and Web apps. Even though those apps provide similar features to the end user, using their native version or Web counterpart might…
Programmable circuits such as general-purpose processors or FPGAs have their end-user energy efficiency strongly dependent on the program that they execute. Ultimately, it is the programmer's ability to code and, in the case of general…
Building energy efficient software is an increasingly important task for mobile developers. However, a cumulative body of knowledge of techniques that support this goal does not exist. We conduct a systematic literature review to gather…
The web has become a ubiquitous application development platform for mobile systems. Yet, web access on mobile devices remains an energy-hungry activity. Prior work in the field mainly focuses on the initial page loading stage, but fails to…
Mobile users today interact with a variety of mobile device types including smartphones, tablets, smartwatches, and others. However research on mobile device type substitution has been limited in several respects including a lack of…
Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent…
Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at…
Monitoring, understanding, and optimizing the energy consumption of Machine Learning (ML) are various reasons why it is necessary to evaluate the energy usage of ML. However, there exists no universal tool that can answer this question for…
This paper explores the feasibility and performance of on-device large language model (LLM) inference on various Apple iPhone models. Amidst the rapid evolution of generative AI, on-device LLMs offer solutions to privacy, security, and…
In recent years,Large Language Models (LLMs) have significantly improved in generating high-quality code, enabling their integration into developers' Integrated Development Environments (IDEs) as code assistants. These assistants, such as…
The power that machine learning models consume when making predictions can be affected by a model's architecture. This paper presents various estimates of power consumption for a range of different activation functions, a core factor in…
With the rapid development of large language models (LLMs), which possess powerful natural language processing and generation capabilities, LLMs are poised to provide more natural and personalized user experiences. Their deployment on…