alexlebens/infrastructure
1
0
Fork 0
Code Issues 1 Pull Requests 8 Actions Packages Projects Releases Wiki Activity

disable extra server

Browse Source
This commit is contained in:
Alex Lebens
2025-02-28 11:50:42 -06:00
parent 6b67c2d037
commit 24a4e58054
1 changed files with 108 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

216
clusters/cl01tl/platform/ollama/values.yaml
View File

@@ -37,80 +37,80 @@ ollama:
limits: limits:
cpu: 4 cpu: 4
gpu.intel.com/i915: 1 gpu.intel.com/i915: 1
server-2: # server-2:
type: deployment # type: deployment
replicas: 1 # replicas: 1
strategy: Recreate # strategy: Recreate
revisionHistoryLimit: 3 # revisionHistoryLimit: 3
pod: # pod:
labels: # labels:
ollama-type: server # ollama-type: server
affinity: # affinity:
podAntiAffinity: # podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution: # requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector: # - labelSelector:
matchExpressions: # matchExpressions:
- key: ollama-type # - key: ollama-type
operator: In # operator: In
values: # values:
- server # - server
topologyKey: kubernetes.io/hostname # topologyKey: kubernetes.io/hostname
containers: # containers:
main: # main:
image: # image:
repository: ollama/ollama # repository: ollama/ollama
tag: 0.5.12 # tag: 0.5.12
pullPolicy: IfNotPresent # pullPolicy: IfNotPresent
env: # env:
- name: OLLAMA_KEEP_ALIVE # - name: OLLAMA_KEEP_ALIVE
value: 24h # value: 24h
- name: OLLAMA_HOST # - name: OLLAMA_HOST
value: 0.0.0.0 # value: 0.0.0.0
resources: # resources:
requests: # requests:
cpu: 100m # cpu: 100m
memory: 1Gi # memory: 1Gi
gpu.intel.com/i915: 1 # gpu.intel.com/i915: 1
limits: # limits:
cpu: 4 # cpu: 4
gpu.intel.com/i915: 1 # gpu.intel.com/i915: 1
server-3: # server-3:
type: deployment # type: deployment
replicas: 1 # replicas: 1
strategy: Recreate # strategy: Recreate
revisionHistoryLimit: 3 # revisionHistoryLimit: 3
pod: # pod:
labels: # labels:
ollama-type: server # ollama-type: server
affinity: # affinity:
podAntiAffinity: # podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution: # requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector: # - labelSelector:
matchExpressions: # matchExpressions:
- key: ollama-type # - key: ollama-type
operator: In # operator: In
values: # values:
- server # - server
topologyKey: kubernetes.io/hostname # topologyKey: kubernetes.io/hostname
containers: # containers:
main: # main:
image: # image:
repository: ollama/ollama # repository: ollama/ollama
tag: 0.5.12 # tag: 0.5.12
pullPolicy: IfNotPresent # pullPolicy: IfNotPresent
env: # env:
- name: OLLAMA_KEEP_ALIVE # - name: OLLAMA_KEEP_ALIVE
value: 24h # value: 24h
- name: OLLAMA_HOST # - name: OLLAMA_HOST
value: 0.0.0.0 # value: 0.0.0.0
resources: # resources:
requests: # requests:
cpu: 100m # cpu: 100m
memory: 1Gi # memory: 1Gi
gpu.intel.com/i915: 1 # gpu.intel.com/i915: 1
limits: # limits:
cpu: 4 # cpu: 4
gpu.intel.com/i915: 1 # gpu.intel.com/i915: 1
web: web:
type: deployment type: deployment
replicas: 1 replicas: 1
@@ -179,20 +179,20 @@ ollama:
port: 11434 port: 11434
targetPort: 11434 targetPort: 11434
protocol: HTTP protocol: HTTP
server-2: # server-2:
controller: server-2 # controller: server-2
ports: # ports:
http: # http:
port: 11434 # port: 11434
targetPort: 11434 # targetPort: 11434
protocol: HTTP # protocol: HTTP
server-3: # server-3:
controller: server-3 # controller: server-3
ports: # ports:
http: # http:
port: 11434 # port: 11434
targetPort: 11434 # targetPort: 11434
protocol: HTTP # protocol: HTTP
web: web:
controller: web controller: web
ports: ports:
@@ -226,26 +226,26 @@ ollama:
main: main:
- path: /root/.ollama - path: /root/.ollama
readOnly: false readOnly: false
server-2: # server-2:
storageClass: ceph-block # storageClass: ceph-block
accessMode: ReadWriteOnce # accessMode: ReadWriteOnce
size: 40Gi # size: 40Gi
retain: true # retain: true
advancedMounts: # advancedMounts:
server-2: # server-2:
main: # main:
- path: /root/.ollama # - path: /root/.ollama
readOnly: false # readOnly: false
server-3: # server-3:
storageClass: ceph-block # storageClass: ceph-block
accessMode: ReadWriteOnce # accessMode: ReadWriteOnce
size: 40Gi # size: 40Gi
retain: true # retain: true
advancedMounts: # advancedMounts:
server-3: # server-3:
main: # main:
- path: /root/.ollama # - path: /root/.ollama
readOnly: false # readOnly: false
web-data: web-data:
storageClass: ceph-block storageClass: ceph-block
accessMode: ReadWriteOnce accessMode: ReadWriteOnce