New RunLLM response generated: >>>*# Question* Hi 👋 I’m setting up the integration with Ray, and it seems to work nicely when creating a fresh RayCluster (using

@task(task_config=RayJobConfig(worker_node_config=[WorkerNodeConfig(…)]))

). I can see the cluster starting, the job getting scheduled and distributed, and completing successfully. I’m having trouble with using an existing RayCluster (in the same cluster) though. What is the correct approach for that? From the docs here I read that I should be able to use

@task(task_config=RayJobConfig(address="<RAY_CLUSTER_ADDRESS>"))

. However when trying that it seems

worker_node_config

is a required argument. I tried using an empty list instead:

@task(
    container_image=...,
    task_config=RayJobConfig(
        worker_node_config=[],  # No need to create a Ray cluster but argument is required, maybe just setting to empty list helps?
        address="kuberay-cluster-head-svc.kuberay.svc.cluster.local:8265",
        runtime_env=...
    ),
)

But then it tries to start a new RayCluster instead of using the existing one found at `address`:

❯ k get <http://rayclusters.ray.io|rayclusters.ray.io> -A
NAMESPACE             NAME                                         DESIRED WORKERS   AVAILABLE WORKERS   CPUS   MEMORY   GPUS   STATUS   AGE
<flyte-project-<flyte-domain>   ahvfr924w8k2vgvf97wp-n0-0-raycluster-crb9z                                         100m   500Mi    0      ready    2m25s
kuberay               kuberay-cluster                              1                 1                   2      3G       0      ready    3h37m
...

# Answer To use an existing RayCluster with Flyte, you should specify the

address

parameter in the

RayJobConfig

to connect to the existing cluster. However, the

worker_node_config

is typically used to define new clusters, and setting it to an empty list might not prevent Flyte from attempting to create a new cluster. According to Flyte documentation, you can connect to an existing Ray cluster by specifying the

address

in the

RayJobConfig

. However, the current implementation might not fully support this use case, as it seems to default to creating a new cluster. Would you like more details on how to potentially work around this issue or further explore the configuration options? Sources: - Flyte Ray Plugin Documentation Slack Link https://.slack.com/archives/CP2HDHKE1/p1729250994.610059 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.