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

Building LocalStack with LocalStack

LocalStack’s core cloud emulator allows us to run our own cloud application - including its infrastructure - locally, which provides an efficient developer experience at the start of the entire software development lifecycle (SDLC). This experience enables us to build our product features in a way that closely matches what our customers are looking for — a comprehensive developer platform that facilitates local multi-cloud development across different providers and services.In this session from LocalStack Community Meetup April '24, Lukas Pichler showcases how to use the LocalStack core cloud emulator and other novel solutions, to build, test, and integrate new features in our LocalStack Web Application. He broadly discusses:• Application Overview• How do we enable local cloud development?How do we use LocalStack in CI?• How do we use LocalStack to enable application previews and E2E testing?• Conclusion

Learn More
Learn More
Break It Till You Make It: Introducing Chaos into Your Stack Locally

What happens when your cloud services fail? 💥In this final episode of our series, we dive into the LocalStack Chaos Dashboard to simulate real-world outages—like DynamoDB errors—and see how your app responds under pressure. Learn how to intentionally break your systems locally so you can ship more resilient applications in production.📘 Read the full blog post for step-by-step details: https://localstack-blog-preview-pr-121.surge.sh/break-it-till-you-make-it-chaos-engineering/

Learn More
Learn More
Automate Your Tests with GitHub Actions & LocalStack

Bring your tests to CI/CD with GitHub Actions! In this episode, we’ll show how to integrate LocalStack into your workflow, so your tests run automatically on every push without touching real AWS resources.Whether you're testing Lambda, DynamoDB, S3, or beyond LocalStack makes it possible to run everything locally, even in your CI workflows.🔗 Read the companion blog post: https://blog.localstack.cloud/automate-your-tests-with-github-actions-and-localstack/

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