International Journal of Computer
Trends and Technology

Research Article | Open Access | Download PDF

Volume 72 | Issue 11 | Year 2024 | Article Id. IJCTT-V72I11P114 | DOI : https://doi.org/10.14445/22312803/IJCTT-V72I11P114

Scalable AI Model Deployment with AWS SageMaker and EKS

Joyanta Banerjee, Soumya Barman, Pratik Jain

Received Revised Accepted Published
30 Sep 2024 30 Oct 2024 21 Nov 2024 30 Nov 2024

Citation :

Joyanta Banerjee, Soumya Barman, Pratik Jain, "Scalable AI Model Deployment with AWS SageMaker and EKS," International Journal of Computer Trends and Technology (IJCTT), vol. 72, no. 11, pp. 135-142, 2024. Crossref, https://doi.org/10.14445/22312803/ IJCTT-V72I11P114

Abstract

As businesses increasingly leverage Artificial Intelligence (AI) to drive innovation, the need for scalable, efficient, and secure AI model deployment is critical. AWS SageMaker and Amazon Elastic Kubernetes Service (EKS) offer a robust solution for deploying Machine Learning (ML) models in a scalable and resilient environment. This article explores integrating AWS SageMaker with EKS to create a highly available, containerized infrastructure for AI model deployment. SageMaker simplifies the process of building, training, and tuning ML models, while EKS provides a powerful platform for running these models in production, ensuring scalability through Kubernetes' container orchestration capabilities. Together, they enable enterprises to deploy AI models that can scale seamlessly to meet varying demands, handle high workloads, and maintain performance, all while taking advantage of the cloud-native ecosystem.

Keywords

AI/ML model, AWS, Containers, EKS, Sagemaker, Scalable deployment.

References

[1] What Is Amazon SageMaker? - Amazon SageMaker, Amazon.com, 2024. [Online]. Available: https://docs.aws.amazon.com/sagemaker/latest/dg/whatis.html
[2] using-kubernetes Run Machine Learning Models, AWS Amazon. [Online]. Available: https://aws.amazon.com/blogs/opensource/using-kubernetes-run-machine-learning-models-eks/
[3] Noah Gift, and Alfredo Deza, Practical MLOps, O’Reilly Online Learning, 2021.
[Google Scholar] [Publisher Link]
[4] Sanjeev Ganjihal et al., “Deploy Generative AI Models on Amazon EKS, Amazon Web Services, 2023. [Online]. Available: aws.amazon.com/blogs/containers/deploy-generative-ai-models-on-amazon-eks/
[5] Bilgin Ibryam, and Roland Huß, Kubernetes Patterns, 2nd Ed., Red Hat Developer, 2023. [Online]. Available: https://developers.redhat.com/e-books/kubernetes-patterns
[6] What Is Amazon EKS? - Amazon EKS, Amazon.com, 2024. [Online]. Available: https://docs.aws.amazon.com/eks/latest/userguide/what is-eks.html
[7] What Is Amazon Elastic Container Registry? - Amazon ECR, Amazon.com, 2024. [Online]. Available: https://docs.aws.amazon.com/AmazonECR/latest/userguide/what-is-ecr.html
[8] James Park et al., Reduce Model Deployment Costs by 50% on Average Using the Latest Features of Amazon SageMaker, Amazon Web Services, 2023. [Online]. Available: https://aws.amazon.com/blogs/machine-learning/reduce-model-deployment-costs-by-50-on-average using-sagemakers-latest-features/
[9] Ofir Nachmani, Compare EKS vs. Self-Managed Kubernetes on AWS, Search AWS, TechTarget, 2022. [Online]. Available: https://www.techtarget.com/searchaws/tip/2-options-to-deploy-Kubernetes-on-AWS-EKS-vs-self-managed