AHFE Open AccessComparison of AI Model Serving Efficiency: Response Time and Memory Usage Analysis
Abstract
NLP (Natural Language Processing) models are in increasing demand, making the research into effective serving methods crucial. Particularly, cost efficiency and rapid response times are key factors in the serving process of NLP models. This paper compares various methods for optimizing the serving of NLP models. Three serving methods were applied using REST API, TensorFlow Serving, and TensorFlow.js, and each method's response speed and memory usage were evaluated. This research is thought to provide foundational guidelines for enhancing the efficiency of serving NLP models, aiming to minimize potential issues in the serving process and improve user experience through such studies.
Keywords: TensorFlow Serving, TensorFlow.js, Nodejs, LSTM, GRU
DOI: 10.54941/ahfe1005580
Cite this paper
More from this volume
- Implementing an AI Fatigue Risk Management System for Aviation Maintenance SMS: A Technology Enhanced Critical Process Human Factors Safety Plan
- Deep Learning Forecast of Perceptual Load Using fNIRS Data
- Artificial intelligence in the function of improving port systems
- Formalizing Trust in Artificial Intelligence for Built Environment Decision-Making
- Artificial Intelligence and Design: Innovation, Practical Applications, and Future Creative Horizons
- Supporting Informal Sustainability Learning with AI-assisted Educational Technology
- An assessment of the maintenance of heritage buildings using AI and IoT: a South African perspective
- What if we Could Entangle Drones? Towards the Management of a Swarm of Drones as a Non-Local Quantum Object
- Engaging All Elderly Residents in Community Renewal: Designer Spotlight Interview Tool for LLM Building
- AI Play in Higher Education: Students’ perceptions of play and co-creation of knowledge with generative AI
- Optimizing AI Involvement in Engineering University Courses Based on Students' Personality
- Predictive Model for Partner Agencies Dependency on Food Banks