Hey folks I have a Ray Cluster running on GCP and am relativ

Question

Hey folks I have a Ray Cluster running on GCP and am relatively new to MLOps from reading this blog post <https flyte org blog ray and flyte> I did not fully grasp the benefits of running Ray inside Flyte can some users of both explain the benefits to me

Ketan (kumare3) · Answer

i think the benefits are ephemeral cluster Automatic setup and teardown cluster Cluster has all your python dependencies installed and is reproducible you can create one cluster per execution per user and they can be independent

Ketan (kumare3) · Answer

But you do not have to use Flyte and KubeRay clusters

Ketan (kumare3) · Answer

we infact will be working with Anyscale and others to add Flyte Agent support to send workloads to existing kubernetes clusters

Ketan (kumare3) · Answer

how do you manage the lifecycle of the clusters across multiple users

Petr Pilař · Answer

My usecase is maybe a bit different there are no users other than my service which launches predefined jobs on the cluster

Petr Pilař · Answer

So Ray itself is never exposed to the users

Ketan (kumare3) · Answer

and you want the cluster to be up all the time

Petr Pilař · Answer

Yeah ideally

Ketan (kumare3) · Answer

if so I think adding a Flyte Agent would be easy or run Ray in client mode

Ketan (kumare3) · Answer

the Flyte Ray job is for emphemeral isolated and potentially short lived clusters

Ketan (kumare3) · Answer

Petr Pilař · Answer

I see makes sense Thanks for the advice

Ketan (kumare3) · Answer

or simply run the ray head node in client mode in a flyte pod

Kevin Su · Answer

cc < Yicheng Lu> Ray agent

Yicheng Lu · Answer

working on it