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

Improving Networking in LocalStack

Connecting your applications to LocalStack has not always been easy. In this video, Simon from the LocalStack team discusses how we streamlined the LocalStack networking experience. We discussed the challenges of connecting your applications to LocalStack and how we're simplifying the LocalStack networking experience. Simon also discussed about configurations required for more complex networking setups, and some common networking scenarios, with example configuration for achieving connectivity.

Learn More
Learn More
How to use AWS SDKs with LocalStack

LocalStack integrates with official AWS Software Development Kits (SDKs) so you can connect to LocalStack services using the same application code you use for AWS services. This lets you develop and test your applications locally without connecting to the cloud. In this video, we will talk about how you can connect to LocalStack emulated services using AWS SDKs.

Learn More
Learn More
How to save state in LocalStack?

LocalStack is ephemeral, so when you stop and restart it, all data is lost. You can use certain features to save the state & load it back when you restart LocalStack. This includes saving the local state for S3 buckets, DynamoDB tables, RDS databases and more. In this video, we explore three mechanisms that allow you to save state in LocalStack: persistence, state export and import, and Cloud Pods.

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