BentoML-0.4.9

• Added Tensorflow SavedModel format support
• Added support for s3 based model repository
• New syntax for BentoService#pack, making it easier to work with multiple models
• Fixed REST API server docker image build issue with new release of gunicorn

BentoML-0.4.8

• Fixed an issue with loading Fastai model in FastaiModelArtifact, when the basic_learn submodule is not already imported
• Fixed an issue with creating AWS SageMaker deployment, previously it will fail with KeyError in certain condition

BentoML-0.4.7

• Fixed an issue where SQLAlchemy alembic files are not found in PyPI distribution
• Fixed an issue with SQLAlchemy alembic overwriting BentoML default logging configuration

BentoML-0.4.5

• Improved BentoML module import time by around 3-4x
• List deployments command now shows "age" column denoting how long the deployment has been created
• Fixed a bug where serverless deployment failed to install required plugins

Docs:

• Updated documentation site https://bentoml.readthedocs.io/

BentoML-0.4.4

New Features:

• Support for both Keras and tensorflow.keras module in KerasModelArtifact
• New serialization option for KerasModelArtifact that stores model in json and weights files (by @ghunkins )
• bentoml list deployments provides clean table outputs now
• Support for AWS S3 based BentoML repository (Beta)

Bug fixes:

• Fixed error with old click version #335
• Fixed REST API Server issue on Windows platform #333

BentoML-0.4.3

• Enhancement to Serverless deployment and SageMaker deployment
• Updated default version string format for user-defined BentoService
• Added the versioneer interface on BentoService for users to define a customized versioning format
• Added '--force' option to bentoml deployment delete command
• Updated clipper base image to 0.4.1

For BentoML developers:

• BentoML now packages local BentoML dev branch when bundling a BentoService for deployment

BentoML-0.4.2

• Introduced SklearnModelArtifact, adding more scikit-learn specific optimizations over previous general PickleArtifact
• Fixed a number of issues with AWS Lambda Serverless deployment
• Improved error message and CLI outputs of AWS SageMaker deployment

BentoML-0.4.1

• Fixed an issue with initializing BentoML logging and repository file direcotry

BentoML-0.4.0 Beta

• Redesigned deployment component available now, take a look at the deploy command:bentoml deployment --help

• Multiple image support in ImageHandler

• Yatai Service Beta Release - a new component in BentoML providing a model registry and deployment manager for your BentoService. It's a stateful service that can run in your local machine for a personal project, or hosted on a server and shared by a machine learning team.

BentoML-0.3.4

• Add pip_dependencies option to @bentoml.env decorator, and making it the recommended approach for adding PyPI dependencies
• Fixed an issue related OpenAPI doc spec with ImageHandler

BentoML Developer Notes

• DEV: added versioneer.py for version management, now using git tags to manage releases
• DEV: Yatai service protobufs and generated interfaces are in the REPO now