Re:BentoML: A platform for serving and deploying machine lea...
by chaoyu on Wednesday October 09, 2019 @05:22PM
(#21208239)
Thanks for sharing the project Kevlar1818.
BentoML author here - we are building BentoML to empower Data Scientists to ship prediction services instead of delivering "models" to dev teams. We proposed a workflow that made it easy for data scientists to create and test prediction services and then deploy them to cloud platforms such as AWS Lambda, SageMaker or Docker/Kubernetes.
Re:BentoML: A platform for serving and deploying machine lea...
by suyash on Tuesday October 08, 2019 @06:51PM
(#21198142)
Interesting project, I've heard a lot of good things about GraphPipe for Model Serving with support for multiple languages (Go, Python, Java) https://github.com/oracle/graphpipe
Re:BentoML: A platform for serving and deploying machine lea...
by chaoyu on Wednesday October 09, 2019 @05:28PM
(#21208318)
Graphpipe solves a very unique problem when building ML model serving system, although BentoML is trying to solve a very different problem. We think it would be interesting to support GraphPipe's flatbuffer format in BentoML's REST API model server down the line if people are interested in that.
BentoML author here - we are building BentoML to empower Data Scientists to ship prediction services instead of delivering "models" to dev teams. We proposed a workflow that made it easy for data scientists to create and test prediction services and then deploy them to cloud platforms such as AWS Lambda, SageMaker or Docker/Kubernetes.
Happy to answer more questions, cheers!
https://bentoml.readthedocs.io/en/latest/quickstart.html
https://colab.research.google.com/github/bentoml/BentoML/blo...