Robert RappandClaude Opus 5.5
986f1116fe
ci / test (push) Failing after 22s
Ein Pod je GPU-VM (Embed+Rerank bzw. Chat), Host-Netz mit den Ports aus dem Compose, P2000 fest per UUID (NVIDIA_VISIBLE_DEVICES). Das Device Plugin vergibt nur noch Index 0 (M4000). Rolle gpu-llamacpp: gemeinsame Vorbereitung (prepare.yml), k3s.yml mit Image-Import und Compose-Stopp; gpu-llamacpp.yml bricht ohne -e llamacpp_compose=true ab. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
49 lines
1.6 KiB
YAML
49 lines
1.6 KiB
YAML
# NVIDIA Device Plugin v0.20.1 (Quelle: deployments/static/nvidia-device-plugin.yml des Projekts),
|
|
# ergänzt um runtimeClassName nvidia und nodeSelector knaster.gpu=true (nur die GPU-VMs).
|
|
# Meldet je Knoten die Ressource nvidia.com/gpu, die Pods anfordern können.
|
|
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: nvidia-device-plugin-daemonset
|
|
namespace: kube-system
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
name: nvidia-device-plugin-ds
|
|
updateStrategy:
|
|
type: RollingUpdate
|
|
template:
|
|
metadata:
|
|
labels:
|
|
name: nvidia-device-plugin-ds
|
|
spec:
|
|
runtimeClassName: nvidia
|
|
nodeSelector:
|
|
knaster.gpu: "true"
|
|
tolerations:
|
|
- key: nvidia.com/gpu
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
priorityClassName: system-node-critical
|
|
containers:
|
|
- image: nvcr.io/nvidia/k8s-device-plugin:v0.20.1
|
|
name: nvidia-device-plugin-ctr
|
|
env:
|
|
- name: FAIL_ON_INIT_ERROR
|
|
value: "false"
|
|
# Nur Index 0 (Quadro M4000 in allen GPU-VMs, geprüft in playbooks/gpu-llamacpp-k3s.yml) wird als
|
|
# nvidia.com/gpu vergeben. Die P2000 gehört fest den llama.cpp-Pods (per UUID, Task 6.1).
|
|
- name: NVIDIA_VISIBLE_DEVICES
|
|
value: "0"
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
volumeMounts:
|
|
- name: device-plugin
|
|
mountPath: /var/lib/kubelet/device-plugins
|
|
volumes:
|
|
- name: device-plugin
|
|
hostPath:
|
|
path: /var/lib/kubelet/device-plugins
|