How do I deploy DioulaD/falcon-7b-instruct-qlora-ge-dq-v2 using RayClusters?
I created the below yaml for RayService but it seems to have scheduling issues.
apiVersion: ray.io/v1alpha1
kind: RayCluster
metadata:
name: ray-cluster
spec:
rayVersion: "2.3.0"
headGroupSpec:
serviceType: RayService # Use RayService type here
rayStartParams:
dashboard-host: "0.0.0.0"
...
template:
metadata:
labels:
app: ray-head
spec:
containers:
- name: ray-head
image: rayproject/ray-ml:2.3.0
resources:
limits:
cpu: 14
memory: 54Gi
requests:
cpu: 14
memory: 54Gi
ports:
- containerPort: 6379
name: gcs
- containerPort: 8265
name: dashboard
- containerPort: 10001
name: client
- containerPort: 8000
name: serve
...
workerGroupSpecs:
- groupName: worker-group
replicas: 1
minReplicas: 1
maxReplicas: 5
rayStartParams:
# Additional Ray start parameters for workers, if needed
...
template:
metadata:
labels:
app: ray-worker
spec:
containers:
- name: ray-worker
image: rayproject/ray-ml:2.3.0
resources:
limits:
cpu: 7
memory: 27Gi
requests:
cpu: 7
memory: 27Gi
...