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

How Cloud Developers Actually Work Without Breaking Everything

Real cloud developers aren’t pushing straight to AWS.They’re building and testing everything locally before a single deploy goes live.This episode breaks down the modern cloud dev workflow and how tools like LocalStack make it possible to move fast without burning money (or trust).Learn how local-first dev culture is changing the cloud game.

Learn More
Learn More
Handwritten digit recognition using MNIST model and Sagemaker on LocalStack

LocalStack Applications in Developer Hub provides sample templates to help LocalStack users adopt real-world scenarios to rapidly and conveniently create, configure, and deploy applications locally. ## Getting startedIn this demo, we will setup a Sagemaker on Localstack

Learn More
Learn More
Getting started with the LocalStack Model Context Protocol (MCP) Server

What if your AI coding assistant could not only write infrastructure code, but also deploy it, test it, and fix issues automatically — all on your local machine? That's exactly what the LocalStack MCP Server makes possible.In this session, we'll introduce the LocalStack Model Context Protocol (MCP) Server, a new tool that lets AI agents manage your entire local cloud development lifecycle through a conversational interface. You'll learn:What MCP is and why it's a game-changer for AI-assisted developmentHow the LocalStack MCP Server turns manual cloud tasks into automated workflowsHow to set up and configure the server with your favorite AI editor (Cursor, VS Code, etc.)Real-world demos: deploying CDK apps, analyzing logs, running chaos tests, managing state with Cloud Pods, and more.Through hands-on examples, we'll walk through a complete workflow where an AI agent deploys a serverless application, verifies resources, troubleshoots issues, and tests resilience, all without leaving the conversation.If you've ever wished your AI assistant could do more than just generate code, this talk will show you what's possible when agents can actually manage your local cloud environment.

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