peterghaddad

@jjyao understood. The CLI should have the ability to pass metadata similar to the Ray Client. `ray.init` enables users to pass metadata, is this possible for us to contribute for...

@ucdmkt i'm with you. I plan on working these unit tests today and early next week. This one should be good to go shortly, but good either way. I do...

@sihanwang41 Still seeing this behavior in Ray 2.3.0 when using serve.run for multiple deployments. Can you confirm you this functionality working?

@sihanwang41 I am using the example on the homepage of the Ray serve docs. Tasking two deployments and running serve.run twice Also in these docs: https://docs.ray.io/en/releases-2.4.0/serve/model_composition.html#serve-model-composition-deployment-graph ``` serve.run(node): This Python...

It seems like the above will randomly choose to delete one, and redeploy the other. Using the following works. ``` serve.run(Test.options().bind(msg="test"), name="my_app1", route_prefix="/app1") serve.run(MyModelDeployment.options().bind(msg="test"), name="my_app2", route_prefix="/app2") ``` Is anyone else...

@DmitriGekhtman would MCAD work for long-lived clusters? i.e say we have a Ray Cluster and we submit a job to the cluster. This job tells the autoscaler to spawn 5...

@simonsays1980 addressed feedback! Let me know if there is anymore feedback!

> > @simonsays1980 addressed feedback! Let me know if there is anymore feedback! > > @peterghaddad Thanks for the comments! So, for the error occuring in the new stack we...

@dkunz49 I ran the example, and is working on my side. I am running Python 3.9 but my gymansium and ray version match.

@jhasm I don't want to speak for others, but believe serve will be critical to ensure 100% uptime during upgrades of Ray Cluster versions. The way a model is served...