Files
Will Anderson 91bfc42989 ops: scale down all non-critical services — dedicate resources to Neuron
Scaled to replicas: 0: fornax (coordinator/ui/workers), jellyfin via media,
overseerr, plex, radarr, sonarr, bazarr, prowlarr, flaresolverr, ollama,
harmonic-wordpress, docuseal, listmonk, memos, plane, redpanda, wp-coordinator
2026-04-24 20:07:41 -05:00

56 lines
1.0 KiB
YAML

apiVersion: apps/v1
kind: Deployment
metadata:
name: ollama
namespace: ollama
labels:
app: ollama
spec:
replicas: 0
strategy:
type: Recreate
selector:
matchLabels:
app: ollama
template:
metadata:
labels:
app: ollama
spec:
containers:
- name: ollama
image: ollama/ollama:latest
ports:
- containerPort: 11434
env:
- name: NVIDIA_VISIBLE_DEVICES
value: all
volumeMounts:
- name: models
mountPath: /root/.ollama
resources:
requests:
memory: 2Gi
cpu: 500m
limits:
memory: 8Gi
cpu: "4"
volumes:
- name: models
persistentVolumeClaim:
claimName: ollama-models
---
apiVersion: v1
kind: Service
metadata:
name: ollama
namespace: ollama
spec:
selector:
app: ollama
ports:
- port: 11434
targetPort: 11434
nodePort: 31434
type: NodePort