Introduce basic helm chart

Signed-off-by: Wilfried Roset <wilfriedroset@users.noreply.github.com>

helm/charts/text-generation-inference/.helmignore

@@ -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/

helm/charts/text-generation-inference/Chart.yaml

@@ -0,0 +1,29 @@
+apiVersion: v2
+name: text-generation-inference
+description: A Helm chart Huggingface's text generation inference
+type: application
+version: 0.1.0
+appVersion: "1.1.0"
+kubeVersion: "^1.27.0-0"
+home: https://github.com/huggingface/text-generation-inference
+annotations:
+  "artifacthub.io/license": HFOILv1.0
+  "artifacthub.io/links": |
+    - name: Upstream Project
+      url: https://github.com/huggingface/text-generation-inference
+    - name: Documentation
+      url: https://huggingface.co/docs/text-generation-inference/index
+maintainers:
+  - name: wilfriedroset
+keywords:
+  - bloom
+  - deep-learning
+  - falcon
+  - gpt
+  - inference
+  - inference
+  - llm
+  - nlp
+  - pytorch
+  - starcoder
+  - transformer

helm/charts/text-generation-inference/README.md

@@ -0,0 +1,27 @@
+# Text Generation Inference chart
+
+Helm chart for deploying [Text Generation Inference](https://huggingface.co/docs/text-generation-inference) to Kubernetes.
+
+## Installation
+### Starcoder
+
+Here is an example of the values to pass to the chart in order to deploy [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b)
+```yaml
+---
+args:
+  - "--model-id"
+  - "bigcode/starcoderbase-7b"
+  - "--num-shard"
+  - "1"
+
+env:
+  HUGGING_FACE_HUB_TOKEN: hf_FIXME
+
+persistence:
+  storageClassName: "default"
+  accessModes: ["ReadWriteOnce"]
+  storage: 150Gi
+```
+```shell
+helm install -f values.yaml startcoder .
+```

helm/charts/text-generation-inference/templates/NOTES.txt

@@ -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 "text-generation-inference.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "text-generation-inference.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "text-generation-inference.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 "text-generation-inference.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 }}

helm/charts/text-generation-inference/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "text-generation-inference.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 "text-generation-inference.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 "text-generation-inference.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "text-generation-inference.labels" -}}
+helm.sh/chart: {{ include "text-generation-inference.chart" . }}
+{{ include "text-generation-inference.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "text-generation-inference.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "text-generation-inference.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "text-generation-inference.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "text-generation-inference.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

helm/charts/text-generation-inference/templates/ingress.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "text-generation-inference.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 "text-generation-inference.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 }}

helm/charts/text-generation-inference/templates/poddisruptionbudget.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.podDisruptionBudget }}
+apiVersion: policy/v1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ include "text-generation-inference.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "text-generation-inference.labels" . | nindent 4 }}
+    {{- with .Values.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  {{- with .Values.podDisruptionBudget.minAvailable }}
+  minAvailable: {{ . }}
+  {{- end }}
+  {{- with .Values.podDisruptionBudget.maxUnavailable }}
+  maxUnavailable: {{ . }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "text-generation-inference.selectorLabels" . | nindent 6 }}
+{{- end }}

helm/charts/text-generation-inference/templates/service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "text-generation-inference.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "text-generation-inference.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: {{ .Values.service.targetPort }}
+      protocol: TCP
+      name: http
+  selector:
+    {{- include "text-generation-inference.selectorLabels" . | nindent 4 }}

helm/charts/text-generation-inference/templates/statefulset.yaml

@@ -0,0 +1,55 @@
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: {{ include "text-generation-inference.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "text-generation-inference.labels" . | nindent 4 }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  serviceName: text-generation-inference
+  selector:
+    matchLabels:
+      {{- include "text-generation-inference.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      name: text-generation-inference
+      labels:
+        {{- include "text-generation-inference.selectorLabels" . | nindent 8 }}
+    spec:
+      containers:
+        - name: text-generation-inference
+          image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+          imagePullPolicy: {{ .Values.image.imagePullPolicy }}
+          ports:
+            - containerPort: 80
+          command:
+            - "text-generation-launcher"
+            {{- range .Values.args }}
+            - {{ . | quote }}
+            {{- end }}
+          env:
+          {{- range $key, $value := .Values.env }}
+            - name: {{ $key }}
+              value: {{ $value | quote }}
+          {{- end }}
+          volumeMounts:
+            - mountPath: "/data"
+              name: storage
+      volumes:
+        - name: storage
+          persistentVolumeClaim:
+            claimName: storage
+      restartPolicy: Always
+  volumeClaimTemplates:
+    - metadata:
+        name: storage
+      spec:
+        accessModes:
+          {{- range .Values.persistence.accessModes }}
+          - {{ . | quote }}
+          {{- end }}
+        storageClassName: {{ .Values.persistence.storageClassName }}
+        resources:
+          requests:
+            storage: {{ .Values.persistence.storage }}

helm/charts/text-generation-inference/values.yaml

@@ -0,0 +1,69 @@
+---
+replicaCount: 1
+
+image:
+  repository: ghcr.io/huggingface/text-generation-inference
+  tag: "1.1.0"
+  pullPolicy: IfNotPresent
+
+nameOverride: ""
+fullnameOverride: ""
+
+service:
+  type: ClusterIP
+  port: 80
+
+resources:
+  limits:
+    nvidia.com/gpu: "1"
+  requests:
+    nvidia.com/gpu: "1"
+
+args:
+  []
+  # See: https://huggingface.co/docs/text-generation-inference/basic_tutorials/launcher
+  # - "--model-id"
+  # - "bigcode/starcoderbase-7b"
+  # - "--revision"
+  # - "4ab631381edb607557cbb04b6e9a225bad16807c"
+  # - "--num-shard"
+  # - "1"
+
+env:
+  {}
+  # See: https://huggingface.co/settings/tokens
+  # HUGGING_FACE_HUB_TOKEN: xxx
+
+ingress:
+  enabled: false
+  className: ""
+  annotations:
+    {}
+    # kubernetes.io/ingress.class: nginx
+    # kubernetes.io/tls-acme: "true"
+  hosts:
+    - host: chart-example.local
+      paths:
+        - path: /
+          pathType: Prefix
+          # backend:
+          #   service:
+          #     name: text-generation-inference
+          #     port:
+          #       number: 80
+  tls: []
+  #  - secretName: chart-example-tls
+  #    hosts:
+  #      - chart-example.local
+
+persistence:
+  storageClassName: "default"
+  accessModes: ["ReadWriteOnce"]
+  storage: 10Gi
+
+## See `kubectl explain poddisruptionbudget.spec` for more
+## ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/
+podDisruptionBudget:
+  apiVersion: "policy/v1"
+  minAvailable: 1
+  maxUnavailable: 1