Thanks

Try with this version, it should work. Version: 1.0.0a6 @Deepak Dhiman

@Suhas I tried with these version. I get below error:

This message was deleted.

Am I doing something wrong

https://pypi.org/project/bentoml/#history Check here for versions, your problem might be because of your OS version. @Deepak Dhiman

It worked @Suhas. Thank you 🙂

This message was deleted.

This message was deleted.

This message was deleted.

This message was deleted.

Hello, can anyone confirm pytorch=1.9.0 and transformers=4.17.0 is supported by bentoml

This message was deleted.

set the channel topic: This channel will also be used for general announcements from BentoML team. Follow us on twitter! https://twitter.com/bentomlai

set the channel topic: This channel is used for general announcements from BentoML team.

set the channel description: Follow us on twitter! https://twitter.com/bentomlai

set the channel topic: This channel is used for general announcements from BentoML team. For support and general questions, please use the #support channel.

Hi <!channel>! BentoML 1.0.0a7 has just been released with a number of improvements and bug fixes. The two most significant changes are: • BREAKING CHANGE: Default serving port has been changed to 3000 ◦ This is due to an issue with new MacOS where 5000 port is always in use. ◦ This will affect default serving port when deploying with Docker. Existing 1.0 preview release users will need to either change deployment config to use port 3000, or pass

--port 5000

to the container command, in order to use the previous default port setting. • New import/export API is available now! ◦ Users can now export models and bentos from local store to a standalone file ◦ Lean more via

bentoml export --help

and

bentoml models export --help

We’ve also recently released Yatai version 0.2.1, with major refactoring around the deployment controller. Users can now create Bento deployments directly via

kubectl

and Kubernetes resource YAML file, in addition to the Yatai Web UI and REST API:

# my_deployment.yaml
apiVersion: <http://serving.yatai.ai/v1alpha1|serving.yatai.ai/v1alpha1>
kind: BentoDeployment
metadata:
  name: demo
spec:
  bento_tag: iris_classifier:3oevmqfvnkvwvuqj
  resources:
    limits:
      cpu: 1000m
    requests:
      cpu: 500m

Apply deployment to your cluster:

kubeclt apply -f my_deployment.yaml

This will make it easy for DevOps to customize BentoML deployments on Kubernetes cluster, with additional k8s resources such as credentials, db, policies and other services. On the

bentoctl

project, we are working on a major new version which embraces a workflow based on terraform, to simplify deploying Bentos to any cloud platforms, such as AWS EC2, Lambda, Sagemaker, Azure, GCP, Heroku, etc. If you are interested in learning more or help with beta testing, definitely chat with @Bo and @jjmachan.

This message was deleted.

This message was deleted.

Hello BentoML community! We're happy to announce that we've released our first blog post! This first piece talks about the broad set of benefits offered by BentoML. In the future we'll be deep diving into lots of different topics. Would love your support, thanks! Twitter Post Linkedin Post

This message was deleted.

This message was deleted.

This message was deleted.

Our intern @Spencer Churchill just wrote up a nice blog post on model reproducibility and the concerns that BentoML helps address out of the box: https://l.bentoml.com/4196 Cool story too about building a covid cough prediction model!

Question: Is there a way to call an instance of

BentoService

directly as a python object, instead of utilizing http call? I have the source for bentoml packing and I am trying to write a simulation test, but doing it with http call is too slow.

BentomlService.inference_apis[0].infer

seems interesting but can't seem to make it work. on 0.13 btw

Oh figured it out, thanks all! Just needed to call the api function directly.

This message was deleted.

hey guys, im trying to deploy an already trained & exported model onto bentos server for model serving