Chaoyu

Thanks for the feedback @mqk! Deleting models and bentos are on our roadmap, it's a bit tricky because it may break "deployment rollback" feature in some cases, and needs to...

Hi @rishin27 - BentoML internally uses async everywhere for better performance, so this might be an internal issue with BentoML on Yatai, that's not related to user code. May I...

Thanks @rishin27, we will look into this issue more. Ideally by design, if the `bentoml serve` works locally, it should definitely work on Yatai. Note that Yatai is still in...

Hi @rishin27, could you try it again with the latest version of BentoML and Yatai? The issue should be resolved by now.

Hi @TheDarkTrumpet - thank you so much for the feedback. We've been getting tons of feedback on the Yatai architecture lately, particularly on how it fits into existing Kubernetes infrastructure...

Looks like there may be an issue with the yatai-deployment-operator, normally the CRD controller in yatai-deployment-operator should sync deployment metadata with Yatai server so it can show up in the...

https://skryvets.com/blog/2021/03/15/kubernetes-pull-image-from-private-ecr-registry/

> I think you might be able to use assume role, this seems like the doc for it: https://docs.aws.amazon.com/AmazonECR/latest/userguide/security_iam_service-with-iam.html iam role works for simple use cases, it has two limitations:...

> Set this as part of org level config why not bento repo level?

Thanks for the feedback @mqk! Another approach is to save the feature names in the model's `custom_objects` field, here's an example: https://github.com/bentoml/BentoML/tree/main/examples/sklearn/pipeline ```python ... bento_model = bentoml.sklearn.save_model( "20_news_group", grid_search.best_estimator_, signatures={...