When deploying your model into production, you have to care about configuring and maintaining the runtime environment, scaling, monitoring and more – all tasks, which are more related to DevOps than to ML. In some contexts, you can achieve your goals in a much simpler way by establishing a «serverless» approach. We’ll take a look at the cloud services «AWS Lambda», «Google Cloud Functions», and «Azure Functions» and show how they enable running ML inference.
