Hi everyone! For those interested in scaling BentoML deployment on Kubernetes - I’m excited to share that we started a proposal for Yatai version 2.0. Here’re some highlights: • Simplify setup for DevOps teams • Moving from Elastic License 2 to Apache License V2 • Support for Distributed Service deployment mode in BentoML 1.2 • Simplify advanced customization and integration with Cloud Native tools • Call for contribution - this is the perfect time to get involved! More details can be found in https://github.com/bentoml/Yatai/issues/504 And please join #yatai if you’re interested in learning about the progress or help with contribution

Wow, you’re thinking of making Yatai under the Apache 2.0 license??? Thank you so much! So many companies are doing the reverse right now (Seldon, ClearML). Seriously, major respect. Also, @noor assi , @Jay Cui , @Mert Bozkır , @doğan keskin , @Alex Parker , @Jacob Petterle —I’ve been thinking it would be really fun to learn kubernetes to self-host BentoCloud (Yatai)—I’d been looking for a reason to do play with K8s, one reason being that many MLOps tools are deployable into it: Metaflow, ClearML, BentoML, Kubeflow, Seldon, etc. Contributing to BentoCloud would be an amazing way to think deeply about full-stack development and K8s and also get some mentorship/peer review/direction.

Welcome Contributions! Yatai will be drastically different from BentoCloud tho. It will be focused on just the Bento-on-Kubernetes provisioning part for those who needs distributed service deployment and leave out UI, workflow management and optimizations to in-house infra/devops team.