新增 AI 部署方案，备用
This commit is contained in:
Sense T
23
llama-cpp/.helmignore
Normal file
23
llama-cpp/.helmignore
Normal file
@@ -0,0 +1,23 @@
|
||||
# Patterns to ignore when building packages.
|
||||
# This supports shell glob matching, relative path matching, and
|
||||
# negation (prefixed with !). Only one pattern per line.
|
||||
.DS_Store
|
||||
# Common VCS dirs
|
||||
.git/
|
||||
.gitignore
|
||||
.bzr/
|
||||
.bzrignore
|
||||
.hg/
|
||||
.hgignore
|
||||
.svn/
|
||||
# Common backup files
|
||||
*.swp
|
||||
*.bak
|
||||
*.tmp
|
||||
*.orig
|
||||
*~
|
||||
# Various IDEs
|
||||
.project
|
||||
.idea/
|
||||
*.tmproj
|
||||
.vscode/
|
||||
24
llama-cpp/Chart.yaml
Normal file
24
llama-cpp/Chart.yaml
Normal file
@@ -0,0 +1,24 @@
|
||||
apiVersion: v2
|
||||
name: llama-cpp
|
||||
description: A Helm chart for Kubernetes
|
||||
|
||||
# A chart can be either an 'application' or a 'library' chart.
|
||||
#
|
||||
# Application charts are a collection of templates that can be packaged into versioned archives
|
||||
# to be deployed.
|
||||
#
|
||||
# Library charts provide useful utilities or functions for the chart developer. They're included as
|
||||
# a dependency of application charts to inject those utilities and functions into the rendering
|
||||
# pipeline. Library charts do not define any templates and therefore cannot be deployed.
|
||||
type: application
|
||||
|
||||
# This is the chart version. This version number should be incremented each time you make changes
|
||||
# to the chart and its templates, including the app version.
|
||||
# Versions are expected to follow Semantic Versioning (https://semver.org/)
|
||||
version: 0.0.2
|
||||
|
||||
# This is the version number of the application being deployed. This version number should be
|
||||
# incremented each time you make changes to the application. Versions are not expected to
|
||||
# follow Semantic Versioning. They should reflect the version the application is using.
|
||||
# It is recommended to use it with quotes.
|
||||
appVersion: "1.16.0"
|
||||
22
llama-cpp/README.md
Normal file
22
llama-cpp/README.md
Normal file
@@ -0,0 +1,22 @@
|
||||
# TuringPi Llama.cpp Chart
|
||||
|
||||
Deploys [Llama.cpp server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) onto your TuringPi
|
||||
cluster, complete with a persistent volume to store the model files, replication and an ingress. Assumes you have
|
||||
followed the instructions at [docs.turingpi.com](https://docs.turingpi.com/docs/how-to-plan-kubernetes-installation) to
|
||||
configure Longhorn, MetaLB and Traefik. By default, uses `lmstudio-ai/gemma-2b-it-GGUF` model, but this can be
|
||||
overridden with custom values.
|
||||
|
||||
## Installation
|
||||
|
||||
```shell
|
||||
helm install llama-cpp https://elepedus.github.io/llama-cpp/llama-cpp-0.0.1.tgz --namespace=llama-cpp
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
By default, the ingress exposes the web UI at `llama.cluster.local`, at the same IP address as you configured
|
||||
for `cluster.local` Make sure to update your `/etc/hosts` file so the new subdomain is accessible:
|
||||
|
||||
```
|
||||
10.0.0.70 turing-cluster turing-cluster.local llama.cluster llama.cluster.local
|
||||
```
|
||||
22
llama-cpp/templates/NOTES.txt
Normal file
22
llama-cpp/templates/NOTES.txt
Normal file
@@ -0,0 +1,22 @@
|
||||
1. Get the application URL by running these commands:
|
||||
{{- if .Values.ingress.enabled }}
|
||||
{{- range $host := .Values.ingress.hosts }}
|
||||
{{- range .paths }}
|
||||
http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- else if contains "NodePort" .Values.service.type }}
|
||||
export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "llama-cpp.fullname" . }})
|
||||
export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
|
||||
echo http://$NODE_IP:$NODE_PORT
|
||||
{{- else if contains "LoadBalancer" .Values.service.type }}
|
||||
NOTE: It may take a few minutes for the LoadBalancer IP to be available.
|
||||
You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "llama-cpp.fullname" . }}'
|
||||
export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "llama-cpp.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
|
||||
echo http://$SERVICE_IP:{{ .Values.service.port }}
|
||||
{{- else if contains "ClusterIP" .Values.service.type }}
|
||||
export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "llama-cpp.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
|
||||
export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
|
||||
echo "Visit http://127.0.0.1:8080 to use your application"
|
||||
kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
|
||||
{{- end }}
|
||||
62
llama-cpp/templates/_helpers.tpl
Normal file
62
llama-cpp/templates/_helpers.tpl
Normal file
@@ -0,0 +1,62 @@
|
||||
{{/*
|
||||
Expand the name of the chart.
|
||||
*/}}
|
||||
{{- define "llama-cpp.name" -}}
|
||||
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create a default fully qualified app name.
|
||||
We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
|
||||
If release name contains chart name it will be used as a full name.
|
||||
*/}}
|
||||
{{- define "llama-cpp.fullname" -}}
|
||||
{{- if .Values.fullnameOverride }}
|
||||
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
|
||||
{{- else }}
|
||||
{{- $name := default .Chart.Name .Values.nameOverride }}
|
||||
{{- if contains $name .Release.Name }}
|
||||
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
|
||||
{{- else }}
|
||||
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create chart name and version as used by the chart label.
|
||||
*/}}
|
||||
{{- define "llama-cpp.chart" -}}
|
||||
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Common labels
|
||||
*/}}
|
||||
{{- define "llama-cpp.labels" -}}
|
||||
helm.sh/chart: {{ include "llama-cpp.chart" . }}
|
||||
{{ include "llama-cpp.selectorLabels" . }}
|
||||
{{- if .Chart.AppVersion }}
|
||||
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
|
||||
{{- end }}
|
||||
app.kubernetes.io/managed-by: {{ .Release.Service }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Selector labels
|
||||
*/}}
|
||||
{{- define "llama-cpp.selectorLabels" -}}
|
||||
app.kubernetes.io/name: {{ include "llama-cpp.name" . }}
|
||||
app.kubernetes.io/instance: {{ .Release.Name }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create the name of the service account to use
|
||||
*/}}
|
||||
{{- define "llama-cpp.serviceAccountName" -}}
|
||||
{{- if .Values.serviceAccount.create }}
|
||||
{{- default (include "llama-cpp.fullname" .) .Values.serviceAccount.name }}
|
||||
{{- else }}
|
||||
{{- default "default" .Values.serviceAccount.name }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
80
llama-cpp/templates/deployment.yaml
Normal file
80
llama-cpp/templates/deployment.yaml
Normal file
@@ -0,0 +1,80 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: {{ include "llama-cpp.fullname" . }}
|
||||
labels:
|
||||
{{- include "llama-cpp.labels" . | nindent 4 }}
|
||||
spec:
|
||||
replicas: {{ .Values.replicaCount }}
|
||||
selector:
|
||||
matchLabels:
|
||||
{{- include "llama-cpp.selectorLabels" . | nindent 6 }}
|
||||
template:
|
||||
metadata:
|
||||
{{- with .Values.podAnnotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
labels:
|
||||
{{- include "llama-cpp.labels" . | nindent 8 }}
|
||||
{{- with .Values.podLabels }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
{{- with .Values.imagePullSecrets }}
|
||||
imagePullSecrets:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
securityContext:
|
||||
{{- toYaml .Values.podSecurityContext | nindent 8 }}
|
||||
containers:
|
||||
- name: {{ .Chart.Name }}
|
||||
securityContext:
|
||||
{{- toYaml .Values.securityContext | nindent 12 }}
|
||||
image: {{ printf "%s:%s" .Values.image.repository (.Values.image.tag | default .Chart.AppVersion) }}
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
command: [ "/server"]
|
||||
args:
|
||||
- "--port"
|
||||
- {{ .Values.service.port | quote }}
|
||||
- "--host"
|
||||
- "0.0.0.0"
|
||||
{{- range $key, $value := .Values.llama.args }}
|
||||
{{- if $value }}
|
||||
- "--{{ $key }}"
|
||||
- "{{ $value }}"
|
||||
{{- else }}
|
||||
- "--{{ $key }}"
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
ports:
|
||||
- name: http
|
||||
containerPort: {{ .Values.service.port }}
|
||||
protocol: TCP
|
||||
livenessProbe:
|
||||
{{- toYaml .Values.livenessProbe | nindent 12 }}
|
||||
readinessProbe:
|
||||
{{- toYaml .Values.readinessProbe | nindent 12 }}
|
||||
resources:
|
||||
{{- toYaml .Values.resources | nindent 12 }}
|
||||
{{- with .Values.volumeMounts }}
|
||||
volumeMounts:
|
||||
{{- toYaml . | nindent 12 }}
|
||||
{{- end }}
|
||||
{{- with .Values.volumes }}
|
||||
volumes:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.nodeSelector }}
|
||||
nodeSelector:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.affinity }}
|
||||
affinity:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.tolerations }}
|
||||
tolerations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
61
llama-cpp/templates/ingress.yaml
Normal file
61
llama-cpp/templates/ingress.yaml
Normal file
@@ -0,0 +1,61 @@
|
||||
{{- if .Values.ingress.enabled -}}
|
||||
{{- $fullName := include "llama-cpp.fullname" . -}}
|
||||
{{- $svcPort := .Values.service.port -}}
|
||||
{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
|
||||
{{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
|
||||
{{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
|
||||
apiVersion: networking.k8s.io/v1
|
||||
{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
{{- else -}}
|
||||
apiVersion: extensions/v1beta1
|
||||
{{- end }}
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: {{ $fullName }}
|
||||
labels:
|
||||
{{- include "llama-cpp.labels" . | nindent 4 }}
|
||||
{{- with .Values.ingress.annotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
{{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
|
||||
ingressClassName: {{ .Values.ingress.className }}
|
||||
{{- end }}
|
||||
{{- if .Values.ingress.tls }}
|
||||
tls:
|
||||
{{- range .Values.ingress.tls }}
|
||||
- hosts:
|
||||
{{- range .hosts }}
|
||||
- {{ . | quote }}
|
||||
{{- end }}
|
||||
secretName: {{ .secretName }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
rules:
|
||||
{{- range .Values.ingress.hosts }}
|
||||
- host: {{ .host | quote }}
|
||||
http:
|
||||
paths:
|
||||
{{- range .paths }}
|
||||
- path: {{ .path }}
|
||||
{{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
|
||||
pathType: {{ .pathType }}
|
||||
{{- end }}
|
||||
backend:
|
||||
{{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
|
||||
service:
|
||||
name: {{ $fullName }}
|
||||
port:
|
||||
number: {{ $svcPort }}
|
||||
{{- else }}
|
||||
serviceName: {{ $fullName }}
|
||||
servicePort: {{ $svcPort }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
11
llama-cpp/templates/pvc.yaml
Normal file
11
llama-cpp/templates/pvc.yaml
Normal file
@@ -0,0 +1,11 @@
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: models
|
||||
spec:
|
||||
accessModes:
|
||||
- ReadWriteMany
|
||||
resources:
|
||||
requests:
|
||||
storage: {{ .Values.storage.size }}
|
||||
storageClassName: {{ .Values.storage.storageClass }}
|
||||
13
llama-cpp/templates/service.yaml
Normal file
13
llama-cpp/templates/service.yaml
Normal file
@@ -0,0 +1,13 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: { { include "llama-cpp.fullname" . } }
|
||||
labels: { { - include "llama-cpp.labels" . | nindent 4 } }
|
||||
spec:
|
||||
type: { { .Values.service.type } }
|
||||
ports:
|
||||
- port: { { .Values.service.port } }
|
||||
targetPort: http
|
||||
protocol: TCP
|
||||
name: http
|
||||
selector: { { - include "llama-cpp.selectorLabels" . | nindent 4 } }
|
||||
15
llama-cpp/templates/tests/test-connection.yaml
Normal file
15
llama-cpp/templates/tests/test-connection.yaml
Normal file
@@ -0,0 +1,15 @@
|
||||
apiVersion: v1
|
||||
kind: Pod
|
||||
metadata:
|
||||
name: "{{ include "llama-cpp.fullname" . }}-test-connection"
|
||||
labels:
|
||||
{{- include "llama-cpp.labels" . | nindent 4 }}
|
||||
annotations:
|
||||
"helm.sh/hook": test
|
||||
spec:
|
||||
containers:
|
||||
- name: wget
|
||||
image: busybox
|
||||
command: ['wget']
|
||||
args: ['{{ include "llama-cpp.fullname" . }}:{{ .Values.service.port }}']
|
||||
restartPolicy: Never
|
||||
213
llama-cpp/values.schema.json
Normal file
213
llama-cpp/values.schema.json
Normal file
@@ -0,0 +1,213 @@
|
||||
{
|
||||
"$schema": "http://json-schema.org/schema#",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"affinity": {
|
||||
"type": "object"
|
||||
},
|
||||
"fullnameOverride": {
|
||||
"type": "string"
|
||||
},
|
||||
"image": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"pullPolicy": {
|
||||
"type": "string"
|
||||
},
|
||||
"repository": {
|
||||
"type": "string"
|
||||
},
|
||||
"tag": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"imagePullSecrets": {
|
||||
"type": "array"
|
||||
},
|
||||
"ingress": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"annotations": {
|
||||
"type": "null"
|
||||
},
|
||||
"className": {
|
||||
"type": "string"
|
||||
},
|
||||
"enabled": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"hosts": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"host": {
|
||||
"type": "string"
|
||||
},
|
||||
"paths": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"path": {
|
||||
"type": "string"
|
||||
},
|
||||
"pathType": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tls": {
|
||||
"type": "array"
|
||||
}
|
||||
}
|
||||
},
|
||||
"livenessProbe": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"httpGet": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"path": {
|
||||
"type": "string"
|
||||
},
|
||||
"port": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"initialDelaySeconds": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
},
|
||||
"llama": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"args": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"hf-file": {
|
||||
"type": "string"
|
||||
},
|
||||
"hf-repo": {
|
||||
"type": "string"
|
||||
},
|
||||
"model": {
|
||||
"type": "string"
|
||||
},
|
||||
"n-predict": {
|
||||
"type": "string"
|
||||
},
|
||||
"parallel": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"nameOverride": {
|
||||
"type": "string"
|
||||
},
|
||||
"nodeSelector": {
|
||||
"type": "object"
|
||||
},
|
||||
"podAnnotations": {
|
||||
"type": "object"
|
||||
},
|
||||
"podLabels": {
|
||||
"type": "object"
|
||||
},
|
||||
"podSecurityContext": {
|
||||
"type": "object"
|
||||
},
|
||||
"readinessProbe": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"httpGet": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"path": {
|
||||
"type": "string"
|
||||
},
|
||||
"port": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"replicaCount": {
|
||||
"type": "integer"
|
||||
},
|
||||
"resources": {
|
||||
"type": "object"
|
||||
},
|
||||
"securityContext": {
|
||||
"type": "object"
|
||||
},
|
||||
"service": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"port": {
|
||||
"type": "integer"
|
||||
},
|
||||
"type": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"storage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"size": {
|
||||
"type": "string"
|
||||
},
|
||||
"storageClass": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"tolerations": {
|
||||
"type": "array"
|
||||
},
|
||||
"volumeMounts": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"mountPath": {
|
||||
"type": "string"
|
||||
},
|
||||
"name": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"volumes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string"
|
||||
},
|
||||
"persistentVolumeClaim": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"claimName": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
101
llama-cpp/values.yaml
Normal file
101
llama-cpp/values.yaml
Normal file
@@ -0,0 +1,101 @@
|
||||
# yaml-language-server: $schema=./values.schema.json
|
||||
|
||||
# Default values for llama-cpp.
|
||||
# This is a YAML-formatted file.
|
||||
# Declare variables to be passed into your templates.
|
||||
|
||||
replicaCount: 1
|
||||
|
||||
image:
|
||||
# repository: "local/llama.cpp"
|
||||
repository: "ghcr.io/ggerganov/llama.cpp"
|
||||
pullPolicy: IfNotPresent
|
||||
# Overrides the image tag whose default is the chart appVersion.
|
||||
tag: "server-60cdf40cc32f0ad4cb11e0ca8fd38f3b93d8d640"
|
||||
|
||||
llama:
|
||||
args:
|
||||
model: "/models/gemma-2b-it-q4_k_m.gguf"
|
||||
hf-repo: "lmstudio-ai/gemma-2b-it-GGUF"
|
||||
hf-file: "gemma-2b-it-q4_k_m.gguf"
|
||||
n-predict: "-1"
|
||||
parallel: "2"
|
||||
|
||||
storage:
|
||||
size: 24Gi
|
||||
storageClass: "local-path"
|
||||
imagePullSecrets: []
|
||||
nameOverride: ""
|
||||
fullnameOverride: ""
|
||||
|
||||
podAnnotations: {}
|
||||
podLabels: {}
|
||||
|
||||
podSecurityContext: {}
|
||||
# fsGroup: 2000
|
||||
|
||||
securityContext: {}
|
||||
# capabilities:
|
||||
# drop:
|
||||
# - ALL
|
||||
# readOnlyRootFilesystem: true
|
||||
# runAsNonRoot: true
|
||||
# runAsUser: 1000
|
||||
|
||||
service:
|
||||
type: ClusterIP
|
||||
port: 80
|
||||
|
||||
ingress:
|
||||
enabled: false
|
||||
className: "traefik"
|
||||
annotations:
|
||||
hosts:
|
||||
- host: llama.cluster.local
|
||||
paths:
|
||||
- path: /
|
||||
pathType: ImplementationSpecific
|
||||
tls: []
|
||||
# - secretName: chart-example-tls
|
||||
# hosts:
|
||||
# - chart-example.local
|
||||
|
||||
resources: {}
|
||||
# We usually recommend not to specify default resources and to leave this as a conscious
|
||||
# choice for the user. This also increases chances charts run on environments with little
|
||||
# resources, such as Minikube. If you do want to specify resources, uncomment the following
|
||||
# lines, adjust them as necessary, and remove the curly braces after 'resources:'.
|
||||
# limits:
|
||||
# cpu: 100m
|
||||
# memory: 128Mi
|
||||
# requests:
|
||||
# cpu: 100m
|
||||
# memory: 128Mi
|
||||
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: http
|
||||
initialDelaySeconds: 900
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: http
|
||||
|
||||
# Additional volumes on the output Deployment definition.
|
||||
volumes:
|
||||
- name: "models"
|
||||
persistentVolumeClaim:
|
||||
claimName: "models"
|
||||
|
||||
# Additional volumeMounts on the output Deployment definition.
|
||||
volumeMounts:
|
||||
- name: "models"
|
||||
mountPath: "/models"
|
||||
|
||||
|
||||
nodeSelector: {}
|
||||
|
||||
tolerations: []
|
||||
|
||||
affinity: {}
|
||||
Reference in New Issue
Block a user