Aleksandr Bogomiakov
8e4201621d
Update Kubernetes Services Wiki / Generate and Update K8s Wiki (push) Failing after 1m6s
38 lines
825 B
YAML
38 lines
825 B
YAML
# AMD GPU device plugin: exposes the Strix Halo iGPU of the "ai" node as the
|
|
# amd.com/gpu resource (and injects /dev/kfd and /dev/dri into the pod).
|
|
nfd:
|
|
enabled: false
|
|
|
|
labeller:
|
|
enabled: false
|
|
|
|
dp:
|
|
image:
|
|
repository: docker.io/rocm/k8s-device-plugin
|
|
tag: "1.31.0.9"
|
|
updateStrategy:
|
|
type: RollingUpdate
|
|
rollingUpdate:
|
|
maxUnavailable: 1
|
|
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
|
|
# The ai node carries the label workload/ai=true and the taint workload=ai:NoSchedule
|
|
# (hosts/ai in the nix repo).
|
|
tolerations:
|
|
- key: workload
|
|
operator: Equal
|
|
value: ai
|
|
effect: NoSchedule
|
|
|
|
node_selector_enabled: true
|
|
node_selector:
|
|
homelab.hexor.cy/pool: core
|
|
homelab.hexor.cy/exposure: internal
|
|
kubernetes.io/arch: amd64
|
|
workload/ai: "true"
|