Files
wehub-resource-sync d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:20:55 +08:00

116 lines
3.4 KiB
YAML

{{- if and .Values.ollama.enabled .Values.ollama.gpu.enabled }}
---
# 1. ConfigMap for NVIDIA Device Plugin Configuration
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "sim.fullname" . }}-nvidia-device-plugin-config
namespace: {{ .Release.Namespace }}
labels:
{{- include "sim.labels" . | nindent 4 }}
app.kubernetes.io/component: nvidia-device-plugin
data:
config.yaml: |
version: v1
flags:
{{- if eq .Values.ollama.gpu.strategy "mig" }}
migStrategy: "single"
{{- else }}
migStrategy: "none"
{{- end }}
failOnInitError: false
plugin:
passDeviceSpecs: true
deviceListStrategy: envvar
{{- if eq .Values.ollama.gpu.strategy "time-slicing" }}
sharing:
timeSlicing:
resources:
- name: nvidia.com/gpu
replicas: {{ .Values.ollama.gpu.timeSlicingReplicas | default 5 }}
{{- end }}
---
# 2. NVIDIA Device Plugin DaemonSet for GPU support
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: {{ include "sim.fullname" . }}-nvidia-device-plugin
namespace: {{ .Release.Namespace }}
labels:
{{- include "sim.labels" . | nindent 4 }}
app.kubernetes.io/component: nvidia-device-plugin
spec:
selector:
matchLabels:
{{- include "sim.selectorLabels" . | nindent 6 }}
app.kubernetes.io/component: nvidia-device-plugin
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
{{- include "sim.selectorLabels" . | nindent 8 }}
app.kubernetes.io/component: nvidia-device-plugin
spec:
tolerations:
# Allow scheduling on GPU nodes
- key: nvidia.com/gpu
operator: Exists
effect: NoSchedule
- key: sku
operator: Equal
value: gpu
effect: NoSchedule
nodeSelector:
# Only schedule on nodes with NVIDIA GPUs
accelerator: nvidia
priorityClassName: system-node-critical
volumes:
- name: device-plugin
hostPath:
path: /var/lib/kubelet/device-plugins
- name: dev
hostPath:
path: /dev
- name: sys
hostPath:
path: /sys
# Volume to mount the ConfigMap
- name: nvidia-device-plugin-config
configMap:
name: {{ include "sim.fullname" . }}-nvidia-device-plugin-config
containers:
- name: nvidia-device-plugin
image: nvcr.io/nvidia/k8s-device-plugin:v0.18.2
imagePullPolicy: Always
args:
- "--config-file=/etc/device-plugin/config.yaml"
{{- if eq .Values.ollama.gpu.strategy "mig" }}
env:
- name: NVIDIA_MIG_MONITOR_DEVICES
value: all
{{- end }}
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: ["ALL"]
volumeMounts:
- name: device-plugin
mountPath: /var/lib/kubelet/device-plugins
- name: dev
mountPath: /dev
- name: sys
mountPath: /sys
readOnly: true
- name: nvidia-device-plugin-config
mountPath: /etc/device-plugin/
readOnly: true
resources:
requests:
cpu: 50m
memory: 20Mi
limits:
cpu: 50m
memory: 50Mi
{{- end }}