Green My LLM: Studying the key factors affecting the energy consumption of code assistants
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 GitHub Copilot, deliver real-time code suggestions and can greatly enhance developers' productivity. However, the environmental impact of these tools, in particular their energy consumption, remains a key concern. This paper investigates the energy consumption of LLM-based code assistants by simulating developer interactions with GitHub Copilot and analyzing various configuration factors. We collected a dataset of development traces from 20 developers and conducted extensive software project development simulations to measure energy usage under different scenarios. Our findings reveal that the energy consumption and performance of code assistants are influenced by various factors, such as the number of concurrent developers, model size, quantization methods, and the use of streaming. Notably, a substantial portion of generation requests made by GitHub Copilot is either canceled or rejected by developers, indicating a potential area for reducing wasted computations. Based on these findings, we share actionable insights into optimizing configurations for different use cases, demonstrating that careful adjustments can lead to significant energy savings.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Greenhouse Gas Emissions and its Main Drivers: a Panel Assessment for EU-27 Member States
This paper assesses the effects of greenhouse gas emissions drivers in EU-27 over the period 2010-2019, using a Panel EGLS model with period fixed effects. In particular, we focused our research on studying the effects o…
An Overview of Drone Energy Consumption Factors and Models
At present, there is a growing demand for drones with diverse capabilities that can be used in both civilian and military applications, and this topic is receiving increasing attention. When it comes to drone operations,…
GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation
Large Language Models (LLMs) are becoming integral to daily life, showcasing their vast potential across various Natural Language Processing (NLP) tasks. Beyond NLP, LLMs are increasingly used in software development tas…
Bug fixingCode CompletionCode GenerationCode Translation+1Green vehicle routing problem that jointly optimizes delivery speed and routing based on the characteristics of electric vehicles
The abundance of materials and the development of the economy have led to the flourishing of the logistics industry, but have also caused certain pollution. The research on GVRP (Green vehicle routing problem) for planni…
Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI
Modern AI practices all strive towards the same goal: better results. In the context of deep learning, the term "results" often refers to the achieved accuracy on a competitive problem set. In this paper, we adopt an ide…
Bayesian OptimisationDeep Learning