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

AWS Data Streaming with LocalStack in Action

In this session, Maximillian Hoheiser discussed developing & testing AWS Data Streaming with LocalStack! In this talk, he focused on Kinesis Data Firehose, an AWS service that allows you to extract, transform, and load streaming data into various destinations like Amazon S3.He dived into how to set up testing for Kinesis Firehose and seamlessly integrated it with other services using Boto3 and CDK/CloudFormation. Maximillian led a live demonstration, showcasing how to set up a practical business case, implement it, and rigorously test it using LocalStack.

Learn More
Learn More
Adopting Testcontainers for local development

Local development and testing are significant for engineers who wish to ship confidently onto production environments. Test-driven development (TDD) has been adopted as an essential practice to enforce that and ensure that every code change is validated locally and on CI. This is where we arrive at the Testcontainers libraries that support your tests, providing lightweight, ephemeral instances of common databases, message brokers, web browsers, or anything else that can run in a Docker container. With Testcontainers, available in different popular languages: Java, Go, .NET, JavaScript/Typescript, and Python, you can replicate the production environment on your local machine and test everything (including AWS APIs powered by LocalStack)! Testcontainers ensure that the data access layer, user interface, and application are tested well at each step. In this session, we have looked at Testcontainers and how to adopt them to develop our applications locally and run our integration tests while using LocalStack to provision cloud resources inside a Docker container before pushing your application to production! In the end, we have also discussed how LocalStack and the Java version of Testcontainers play nicely with each other and wind up with updates about the all-new LocalStack release!

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