From DevOps to MLOps: Scaling ML models to 2 Million+ requests per day

The challenge with Machine Learning (ML) models is productionizing. It requires data ingestion, data preparation, model training, model deployment, and monitoring.Adopting MLOps practices is similar to DevOps practices. In MLOps, the workload changes, but some core principles like automation, continuous integration/continuous deployment (CI/CD), and monitoring. Taking DevOps practices, I will discuss the similarities and differences in adopting MLOps practices.In this talk, Chinmay takes a production use case to scale ML models to 2 million+ daily requests. It leverages Google Cloud's (GCP) infrastructure to use its GPU and other services. This talk will help you draw similarities between DevOps and MLOps as a DevOps practitioner and help you learn how to run Machine Learning models at the production scale with best practices.

Related Talks

Unified Kubernetes Support in LocalStack

LocalStack now provides enhanced support for running AWS services in Kubernetes environments. In this presentation from the LocalStack 4.0 community meetup by Simon Walker, we explore how to deploy and manage local AWS resources within Kubernetes clusters with LocalStack, to help developers maintain consistency between development and production environments.The session further covers LocalStack’s Kubernetes integration, including deployment via Helm charts, configuration of services like Lambda and RDS as Kubernetes pods, and networking between components. A demo illustrates provisioning a serverless application (Lambda functions interacting with a MySQL database) using Terraform, with all resources managed within a local Kubernetes cluster.You'll additionally learn the practical approaches for local testing and infrastructure emulation by moving from Docker to Kubernetes-native solutions as well as upcoming features, including broader service support and new container runtime options.## Resources- Documentation: https://docs.localstack.cloud/user-guide/localstack-enterprise/kubernetes-executor/- Get access: https://www.localstack.cloud/contact

Learn More
Learn More
Towards a LocalStack Snowflake emulator—develop your data pipelines locally!

About a year ago we have released the first version of LocalStack Extensions: Extensions are a powerful mechanism to plug additional functionality into LocalStack - ranging from additional service emulators, to value-add features like Chaos Engineering, request logging, cloud resource replication/proxying, and more.Over the last couple of months we have been experimenting with a LocalStack Snowflake emulator extension, which allows to develop and test your Snowflake data pipelines entirely on your local machine!In this talk, Waldemar discusses and demonstrates how you can develop your Snowflake data pipelines locally with LocalStack.

Learn More
Learn More
Testing Terraform Modules in Local and CI Environments with LocalStack

Terraform 1.6 introduced native Terraform tests, but running them against real cloud resources leads to long deployment times and unnecessary costs. With LocalStack's Terraform integration (tflocal), you can validate configurations locally while closely emulating real cloud behaviour. By combining Terraform tests with LocalStack, developers can run integration tests in CI/CD environments, test event-driven serverless workflows, and establish a rapid feedback loop for cloud development.In this presentation, Harsh Mishra provides a hands-on demo of Terraform testing with LocalStack, exploring how to configure tests, validate infrastructure locally, and reduce costs and complexity while improving confidence in deployments.## Resources- Blog: https://blog.localstack.cloud/efficient-infrastructure-testing-localstack-terraform-tests-framework/- Documentation: https://developer.hashicorp.com/terraform/language/tests- tflocal: https://docs.localstack.cloud/user-guide/integrations/terraform/#tflocal-wrapper-script

Learn More
Learn More

Launch yourself in the world of local cloud development

Try for free
Try for free
Talk to Sales
Talk to Sales