Research-Stack/4-Infrastructure/kube/raycluster.yaml
Brandon Schneider c6206b1ba8 docs(kube): update infra docs, RayCluster manifest with nightly GPU images
- infrastructure-status.md: rewrite with current cluster topology (cupfox control-plane,
  neon-64gb/racknerd/steamdeck workers), RayCluster status, Garage storage,
  Caddy edge, open issues
- k3s-cluster-setup.md: fix steamdeck hardware specs (8 vCPU, 14.5 GB RAM)
- raycluster.yaml: upgrade to rayproject/ray:nightly-py313-gpu (multi-arch amd64+arm64),
  add gpu-workers group targeting neon-64gb, add arm64-workers for neon-64gb CPU
- README.md: update build job count (3460 → 3313, verified)

Build: lake build Compiler 3313 jobs, 0 errors
2026-05-30 16:23:13 -05:00

135 lines
3.2 KiB
YAML

apiVersion: ray.io/v1
kind: RayCluster
metadata:
name: raycluster
namespace: ray-system
spec:
rayVersion: "2.41.0.dev0"
headGroupSpec:
serviceType: ClusterIP
rayStartParams:
num-cpus: "0"
dashboard: "false"
template:
spec:
containers:
- name: ray-head
image: rayproject/ray:nightly-py313-gpu
ports:
- containerPort: 6379
name: gcs
- containerPort: 8265
name: dashboard
- containerPort: 10001
name: client
- containerPort: 8000
name: serve
resources:
requests:
cpu: "2"
memory: "4Gi"
limits:
cpu: "4"
memory: "8Gi"
volumeMounts:
- name: dshm
mountPath: /dev/shm
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 2Gi
nodeSelector:
kubernetes.io/hostname: steamdeck
workerGroupSpecs:
- replicas: 1
minReplicas: 0
maxReplicas: 3
groupName: cpu-workers
rayStartParams:
num-cpus: "2"
template:
spec:
containers:
- name: ray-worker
image: rayproject/ray:nightly-py313-gpu
resources:
requests:
cpu: "1"
memory: "1Gi"
limits:
cpu: "2"
memory: "2Gi"
volumeMounts:
- name: dshm
mountPath: /dev/shm
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 1Gi
nodeSelector:
kubernetes.io/hostname: steamdeck
- replicas: 0
minReplicas: 0
maxReplicas: 2
groupName: gpu-workers
rayStartParams:
num-gpus: "1"
template:
spec:
containers:
- name: ray-worker
image: rayproject/ray:nightly-py313-gpu
resources:
requests:
cpu: "2"
memory: "8Gi"
nvidia.com/gpu: "1"
limits:
cpu: "4"
memory: "16Gi"
nvidia.com/gpu: "1"
volumeMounts:
- name: dshm
mountPath: /dev/shm
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 4Gi
nodeSelector:
kubernetes.io/hostname: neon-64gb
tolerations:
- key: "nvidia.com/gpu"
operator: "Exists"
effect: "NoSchedule"
- replicas: 0
minReplicas: 0
maxReplicas: 1
groupName: arm64-workers
rayStartParams:
num-cpus: "4"
template:
spec:
containers:
- name: ray-worker
image: rayproject/ray:nightly-py313-gpu
resources:
requests:
cpu: "4"
memory: "8Gi"
limits:
cpu: "8"
memory: "16Gi"
volumeMounts:
- name: dshm
mountPath: /dev/shm
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 4Gi
nodeSelector:
kubernetes.io/hostname: neon-64gb
kubernetes.io/arch: arm64