https://www.alexanderjunge.net/categories/mlops/ Recent content in Mlops on Alexander Junge's website Hugo -- gohugo.io en-US Wed, 02 Dec 2020 00:00:00 +0000 https://www.alexanderjunge.net/blog/mlflow-sagemaker-deploy/ Wed, 02 Dec 2020 00:00:00 +0000 https://www.alexanderjunge.net/blog/mlflow-sagemaker-deploy/ Deploying a trained machine learning model behind a REST API endpoint is an common problem that needs to be solved on the last mile to getting the model into production. The MLflow package provides a nice abstraction layer that makes deployment via AWS SageMaker (or Microsoft Azure ML or Apache Spark UDF) quite easy. Here follows an example that illustrates how a PyTorch-based pre-trained HuggingFace transformers Extractive Question Answering NLP model can be deployed to an AWS SageMaker endpoint.