Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 46a5d381f3 |
@@ -1,20 +0,0 @@
|
||||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: llamacpp
|
||||
namespace: argocd
|
||||
spec:
|
||||
project: apps
|
||||
destination:
|
||||
namespace: llamacpp
|
||||
server: https://kubernetes.default.svc
|
||||
source:
|
||||
repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
|
||||
targetRevision: HEAD
|
||||
path: k8s/apps/llamacpp
|
||||
syncPolicy:
|
||||
automated:
|
||||
selfHeal: true
|
||||
prune: true
|
||||
syncOptions:
|
||||
- CreateNamespace=true
|
||||
@@ -1,12 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: llamacpp-config
|
||||
data:
|
||||
LLAMA_CACHE: /models
|
||||
LLAMA_ARG_HOST: 0.0.0.0
|
||||
LLAMA_ARG_PORT: "8080"
|
||||
LLAMA_ARG_HF_REPO: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K"
|
||||
LLAMA_ARG_CTX_SIZE: "32768"
|
||||
LLAMA_ARG_FLASH_ATTN: auto
|
||||
LLAMA_ARG_FIT: "on"
|
||||
@@ -1,71 +0,0 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: llamacpp
|
||||
annotations:
|
||||
reloader.stakater.com/auto: "true"
|
||||
labels:
|
||||
app: llamacpp
|
||||
spec:
|
||||
replicas: 1
|
||||
strategy:
|
||||
type: Recreate
|
||||
selector:
|
||||
matchLabels:
|
||||
app: llamacpp
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: llamacpp
|
||||
spec:
|
||||
dnsPolicy: Default
|
||||
nodeSelector:
|
||||
kubernetes.io/hostname: ai.tail2fe2d.ts.net
|
||||
tolerations:
|
||||
- key: workload
|
||||
operator: Equal
|
||||
value: ai
|
||||
effect: NoSchedule
|
||||
containers:
|
||||
- name: llamacpp
|
||||
image: ghcr.io/ggml-org/llama.cpp:server-rocm-b9501
|
||||
imagePullPolicy: IfNotPresent
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: llamacpp-config
|
||||
env:
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: llamacpp-hf-token
|
||||
key: token
|
||||
optional: true
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: 8080
|
||||
protocol: TCP
|
||||
resources:
|
||||
limits:
|
||||
amd.com/gpu: 1
|
||||
startupProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: http
|
||||
failureThreshold: 180
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 5
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: http
|
||||
failureThreshold: 3
|
||||
periodSeconds: 10
|
||||
timeoutSeconds: 5
|
||||
volumeMounts:
|
||||
- name: models
|
||||
mountPath: /models
|
||||
volumes:
|
||||
- name: models
|
||||
hostPath:
|
||||
path: /k8s/llamacpp/models
|
||||
type: DirectoryOrCreate
|
||||
@@ -1,8 +0,0 @@
|
||||
apiVersion: kustomize.config.k8s.io/v1beta1
|
||||
kind: Kustomization
|
||||
|
||||
resources:
|
||||
- app.yaml
|
||||
- configmap.yaml
|
||||
- deployment.yaml
|
||||
- service.yaml
|
||||
@@ -1,15 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: llamacpp
|
||||
labels:
|
||||
app: llamacpp
|
||||
spec:
|
||||
type: ClusterIP
|
||||
selector:
|
||||
app: llamacpp
|
||||
ports:
|
||||
- name: http
|
||||
port: 8080
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
@@ -22,7 +22,7 @@ spec:
|
||||
entryPoints:
|
||||
- websecure
|
||||
routes:
|
||||
- match: Host(`proxy.hexor.cy`)
|
||||
- match: Host(`secret-reader.hexor.cy`)
|
||||
kind: Rule
|
||||
middlewares:
|
||||
- name: auth-proxy
|
||||
@@ -30,16 +30,16 @@ spec:
|
||||
- name: secret-reader
|
||||
port: 80
|
||||
tls:
|
||||
secretName: proxy-tls
|
||||
secretName: secret-reader-tls
|
||||
---
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: proxy-tls
|
||||
name: secret-reader-tls
|
||||
spec:
|
||||
secretName: proxy-tls
|
||||
secretName: secret-reader-tls
|
||||
issuerRef:
|
||||
name: letsencrypt
|
||||
kind: ClusterIssuer
|
||||
dnsNames:
|
||||
- proxy.hexor.cy
|
||||
- secret-reader.hexor.cy
|
||||
|
||||
@@ -9,14 +9,14 @@ resources:
|
||||
helmCharts:
|
||||
- name: ollama
|
||||
repo: https://otwld.github.io/ollama-helm/
|
||||
version: 1.58.0
|
||||
version: 1.49.0
|
||||
releaseName: ollama
|
||||
namespace: ollama
|
||||
valuesFile: ollama-values.yaml
|
||||
includeCRDs: true
|
||||
- name: open-webui
|
||||
repo: https://helm.openwebui.com/
|
||||
version: 14.8.0
|
||||
version: 12.10.0
|
||||
releaseName: openweb-ui
|
||||
namespace: ollama
|
||||
valuesFile: openweb-ui-values.yaml
|
||||
|
||||
@@ -2,8 +2,8 @@ clusterDomain: cluster.local
|
||||
|
||||
extraEnvVars:
|
||||
GLOBAL_LOG_LEVEL: debug
|
||||
OAUTH_PROVIDER_NAME: keycloak
|
||||
OPENID_PROVIDER_URL: https://auth.hexor.cy/auth/realms/hexor/.well-known/openid-configuration
|
||||
OAUTH_PROVIDER_NAME: authentik
|
||||
OPENID_PROVIDER_URL: https://idm.hexor.cy/application/o/openwebui/.well-known/openid-configuration
|
||||
OPENID_REDIRECT_URI: https://ai.hexor.cy/oauth/oidc/callback
|
||||
WEBUI_URL: https://ai.hexor.cy
|
||||
# Allows auto-creation of new users using OAuth. Must be paired with ENABLE_LOGIN_FORM=false.
|
||||
@@ -31,7 +31,7 @@ ollama:
|
||||
- qwen3-vl:8b
|
||||
|
||||
pipelines:
|
||||
enabled: false
|
||||
enabled: true
|
||||
nodeSelector:
|
||||
kubernetes.io/hostname: master.tail2fe2d.ts.net
|
||||
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
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
|
||||
|
||||
tolerations:
|
||||
- key: workload
|
||||
operator: Equal
|
||||
value: ai
|
||||
effect: NoSchedule
|
||||
|
||||
node_selector_enabled: true
|
||||
node_selector:
|
||||
kubernetes.io/arch: amd64
|
||||
kubernetes.io/hostname: ai.tail2fe2d.ts.net
|
||||
@@ -13,24 +13,3 @@ helmCharts:
|
||||
namespace: gpu-system
|
||||
valuesFile: values.yaml
|
||||
includeCRDs: true
|
||||
- name: amd-gpu
|
||||
repo: https://rocm.github.io/k8s-device-plugin/
|
||||
version: 0.21.0
|
||||
releaseName: amd-gpu-device-plugin
|
||||
namespace: gpu-system
|
||||
valuesFile: amd-gpu-values.yaml
|
||||
includeCRDs: true
|
||||
|
||||
patches:
|
||||
- target:
|
||||
group: apps
|
||||
version: v1
|
||||
kind: DaemonSet
|
||||
name: amd-gpu-device-plugin-daemonset
|
||||
namespace: gpu-system
|
||||
patch: |-
|
||||
- op: replace
|
||||
path: /spec/template/spec/nodeSelector
|
||||
value:
|
||||
kubernetes.io/arch: amd64
|
||||
kubernetes.io/hostname: ai.tail2fe2d.ts.net
|
||||
|
||||
@@ -9,12 +9,12 @@ groups = [
|
||||
|
||||
proxy_applications = {
|
||||
secret-reader = {
|
||||
domain = "proxy.hexor.cy"
|
||||
allowed_groups = ["hexor-admin", "app-pass"]
|
||||
domain = "secret-reader.hexor.cy"
|
||||
allowed_groups = ["hexor-guest", "hexor-admin"]
|
||||
}
|
||||
pass = {
|
||||
domain = "pass.hexor.cy"
|
||||
allowed_groups = ["hexor-admin", "app-pass"]
|
||||
allowed_groups = ["hexor-guest", "hexor-admin"]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -40,11 +40,6 @@ oauth2_applications = {
|
||||
web_origins = ["https://gf.hexor.cy"]
|
||||
post_logout_redirect_uris = ["https://gf.hexor.cy/*"]
|
||||
}
|
||||
openwebui = {
|
||||
redirect_uris = ["https://ai.hexor.cy/oauth/oidc/callback"]
|
||||
web_origins = ["https://ai.hexor.cy"]
|
||||
post_logout_redirect_uris = ["https://ai.hexor.cy/*"]
|
||||
}
|
||||
FuruMusic = {
|
||||
redirect_uris = ["https://music.hexor.cy/auth/oidc/callback"]
|
||||
web_origins = ["https://music.hexor.cy"]
|
||||
@@ -61,3 +56,4 @@ oauth2_applications = {
|
||||
post_logout_redirect_uris = ["https://pet.hexor.cy/*", "https://xn--l1acako8eb.xn--p1ai/*", "https://мурняня.рф/*"]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user