bentoml.ai

model serving is the process of applying trained machine learning models at scale for applications. and bentoml.ai is the saas platform providing an end-to-end model serving solution for data science teams, based on our open-source project bentoml. bentoml is an open-source platform for high-performance machine learning model serving. it makes it easy to build production api endpoint for your ml model and supports all major machine learning frameworks, including tensorflow, keras, pytorch, xgboost, scikit-learn, fastai and more. bentoml comes with a high-performance api model server with adaptive micro-batching support, bringing the advantage of batch processing to online serving workloads. it also provides batch serving, model management and model deployment functionality, which gives ml teams an end-to-end model serving solution, with devops best practices baked in.