From b0e5a5c60f8e1208e7239714b82e6a0ee9ff45e8 Mon Sep 17 00:00:00 2001
From: tylertitsworth <tyler.titsworth@intel.com>
Date: Wed, 28 Aug 2024 14:37:42 -0700
Subject: [PATCH 1/3] init tf serving chart
Signed-off-by: tylertitsworth <tyler.titsworth@intel.com>
---
.../charts/tensorflow-serving/.helmignore | 23 ++++++
.../charts/tensorflow-serving/Chart.yaml | 42 ++++++++++
workflows/charts/tensorflow-serving/README.md | 40 ++++++++++
.../tensorflow-serving/templates/NOTES.txt | 22 +++++
.../tensorflow-serving/templates/_helpers.tpl | 51 ++++++++++++
.../templates/deployment.yaml | 80 +++++++++++++++++++
.../tensorflow-serving/templates/ingress.yaml | 75 +++++++++++++++++
.../tensorflow-serving/templates/service.yaml | 28 +++++++
.../templates/tests/test-connection.yaml | 29 +++++++
.../charts/tensorflow-serving/values.yaml | 73 +++++++++++++++++
10 files changed, 463 insertions(+)
create mode 100644 workflows/charts/tensorflow-serving/.helmignore
create mode 100644 workflows/charts/tensorflow-serving/Chart.yaml
create mode 100644 workflows/charts/tensorflow-serving/README.md
create mode 100644 workflows/charts/tensorflow-serving/templates/NOTES.txt
create mode 100644 workflows/charts/tensorflow-serving/templates/_helpers.tpl
create mode 100644 workflows/charts/tensorflow-serving/templates/deployment.yaml
create mode 100644 workflows/charts/tensorflow-serving/templates/ingress.yaml
create mode 100644 workflows/charts/tensorflow-serving/templates/service.yaml
create mode 100644 workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
create mode 100644 workflows/charts/tensorflow-serving/values.yaml
diff --git a/workflows/charts/tensorflow-serving/.helmignore b/workflows/charts/tensorflow-serving/.helmignore
new file mode 100644
index 00000000..0e8a0eb3
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/.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/
diff --git a/workflows/charts/tensorflow-serving/Chart.yaml b/workflows/charts/tensorflow-serving/Chart.yaml
new file mode 100644
index 00000000..e6a61952
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/Chart.yaml
@@ -0,0 +1,42 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: v2
+name: tensorflow-serving-on-intel
+description: TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.
+
+# 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.
+maintainers:
+ - name: tylertitsworth
+ email: tyler.titsworth@intel.com
+ url: https://github.com/tylertitsworth
+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: 0.1.0
+
+# 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"
diff --git a/workflows/charts/tensorflow-serving/README.md b/workflows/charts/tensorflow-serving/README.md
new file mode 100644
index 00000000..853384ef
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/README.md
@@ -0,0 +1,40 @@
+# tensorflow-serving-on-intel
+
+  
+
+TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.
+
+## Maintainers
+
+| Name | Email | Url |
+| ---- | ------ | --- |
+| tylertitsworth | <tyler.titsworth@intel.com> | <https://github.com/tylertitsworth> |
+
+## Values
+
+| Key | Type | Default | Description |
+|-----|------|---------|-------------|
+| deploy.env | object | `{"configMapName":"intel-proxy-config","enabled":true}` | Add Environment mapping |
+| deploy.image | string | `"intel/intel-extension-for-tensorflow:serving-gpu"` | Intel Extension for Tensorflow Serving image |
+| deploy.modelName | string | `""` | Model Name |
+| deploy.modelPath | string | `"/serving"` | Path to Model Folder |
+| deploy.replicas | int | `1` | Number of pods |
+| deploy.resources.limits | object | `{"cpu":"4000m","gpu.intel.com/i915":1,"memory":"1Gi"}` | Maximum resources per pod |
+| deploy.resources.limits."gpu.intel.com/i915" | int | `1` | Intel GPU Device Configuration |
+| deploy.resources.requests | object | `{"cpu":"1000m","memory":"512Mi"}` | Minimum resources per pod |
+| deploy.storage.nfs | object | `{"enabled":false,"path":"nil","readOnly":true,"server":"nil","subPath":"nil"}` | Network File System (NFS) storage for models |
+| fullnameOverride | string | `""` | Full qualified Domain Name |
+| ingress.annotations | object | `{}` | |
+| ingress.className | string | `""` | |
+| ingress.enabled | bool | `false` | |
+| ingress.hosts[0].host | string | `"chart-example.local"` | |
+| ingress.hosts[0].paths[0].path | string | `"/"` | |
+| ingress.hosts[0].paths[0].pathType | string | `"ImplementationSpecific"` | |
+| ingress.tls | list | `[]` | |
+| nameOverride | string | `""` | Name of the serving service |
+| pvc.size | string | `"1Gi"` | Size of the storage |
+| service.port | int | `9090` | Port of the service |
+| service.type | string | `"NodePort"` | Type of service |
+
+----------------------------------------------
+Autogenerated from chart metadata using [helm-docs v1.14.2](https://github.com/norwoodj/helm-docs/releases/v1.14.2)
diff --git a/workflows/charts/tensorflow-serving/templates/NOTES.txt b/workflows/charts/tensorflow-serving/templates/NOTES.txt
new file mode 100644
index 00000000..cbc436df
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/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 "tensorflow-serving.fullname" . }})
+ export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+ echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+ NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+ You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "tensorflow-serving.fullname" . }}'
+ export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "tensorflow-serving.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 "tensorflow-serving.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 }}
diff --git a/workflows/charts/tensorflow-serving/templates/_helpers.tpl b/workflows/charts/tensorflow-serving/templates/_helpers.tpl
new file mode 100644
index 00000000..2afbfd70
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/_helpers.tpl
@@ -0,0 +1,51 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "tensorflow-serving.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 "tensorflow-serving.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 "tensorflow-serving.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "tensorflow-serving.labels" -}}
+helm.sh/chart: {{ include "tensorflow-serving.chart" . }}
+{{ include "tensorflow-serving.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "tensorflow-serving.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "tensorflow-serving.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
diff --git a/workflows/charts/tensorflow-serving/templates/deployment.yaml b/workflows/charts/tensorflow-serving/templates/deployment.yaml
new file mode 100644
index 00000000..e5d91b6c
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/deployment.yaml
@@ -0,0 +1,80 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+ name: {{ include "tensorflow-serving.fullname" . }}
+ labels:
+ {{- include "tensorflow-serving.labels" . | nindent 4 }}
+spec:
+ {{- if not .Values.autoscaling.enabled }}
+ replicas: {{ .Values.deploy.replicas }}
+ {{- end }}
+ selector:
+ matchLabels:
+ {{- include "tensorflow-serving.selectorLabels" . | nindent 6 }}
+ template:
+ metadata:
+ labels:
+ {{- include "tensorflow-serving.labels" . | nindent 8 }}
+ spec:
+ securityContext:
+ fsGroup: 1000
+ runAsUser: 1000
+ containers:
+ - name: tensorflow-serving
+ image: {{ .Values.deploy.image }}
+ {{- if eq .Values.deploy.env.enabled true }}
+ envFrom:
+ - configMapRef:
+ name: {{ .Values.deploy.env.configMapName }}
+ {{- end }}
+ env:
+ - name: MODEL_NAME
+ value: {{ .Values.deploy.modelName }}
+ - name: MODEL_DIR
+ value: {{ .Values.deploy.modelPath }}
+ ports:
+ - name: serving
+ containerPort: {{ .Values.service.port }}
+ volumeMounts:
+ - mountPath: /dev/shm
+ name: dshm
+ {{- if .Values.deploy.storage.nfs.enabled }}
+ - name: model
+ mountPath: /home/model-server/model-store
+ subPath: {{ .Values.deploy.storage.nfs.subPath }}
+ {{- else }}
+ - name: model
+ mountPath: /home/model-server/model-store
+ {{- end }}
+ resources:
+ {{- toYaml .Values.deploy.resources | nindent 12 }}
+ volumes:
+ - name: dshm
+ emptyDir:
+ medium: Memory
+ {{- if .Values.deploy.storage.nfs.enabled }}
+ - name: model
+ nfs:
+ server: {{ .Values.deploy.storage.nfs.server }}
+ path: {{ .Values.deploy.storage.nfs.path }}
+ readOnly: {{ .Values.deploy.storage.nfs.readOnly }}
+ emptyDir: {}
+ {{- else }}
+ - name: model
+ persistentVolumeClaim:
+ claimName: {{ include "tensorflow-serving.fullname" . }}-model-dir
+ {{- end }}
diff --git a/workflows/charts/tensorflow-serving/templates/ingress.yaml b/workflows/charts/tensorflow-serving/templates/ingress.yaml
new file mode 100644
index 00000000..ac9bbc82
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/ingress.yaml
@@ -0,0 +1,75 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "tensorflow-serving.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 "tensorflow-serving.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 }}
diff --git a/workflows/charts/tensorflow-serving/templates/service.yaml b/workflows/charts/tensorflow-serving/templates/service.yaml
new file mode 100644
index 00000000..d878b0c8
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/service.yaml
@@ -0,0 +1,28 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: v1
+kind: Service
+metadata:
+ name: {{ include "tensorflow-serving.fullname" . }}
+ labels:
+ {{- include "tensorflow-serving.labels" . | nindent 4 }}
+spec:
+ type: {{ .Values.service.type }}
+ ports:
+ - name: serving
+ port: {{ .Values.service.port }}
+ targetPort: serving
+ selector:
+ {{- include "tensorflow-serving.selectorLabels" . | nindent 4 }}
diff --git a/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
new file mode 100644
index 00000000..7914869c
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
@@ -0,0 +1,29 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: v1
+kind: Pod
+metadata:
+ name: "{{ include "tensorflow-serving.fullname" . }}-test-connection"
+ labels:
+ {{- include "tensorflow-serving.labels" . | nindent 4 }}
+ annotations:
+ "helm.sh/hook": test
+spec:
+ containers:
+ - name: wget
+ image: busybox
+ command: ['wget']
+ args: ['{{ include "tensorflow-serving.fullname" . }}:{{ .Values.service.port }}']
+ restartPolicy: Never
diff --git a/workflows/charts/tensorflow-serving/values.yaml b/workflows/charts/tensorflow-serving/values.yaml
new file mode 100644
index 00000000..4aef4120
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/values.yaml
@@ -0,0 +1,73 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# -- Name of the serving service
+nameOverride: ""
+# -- Full qualified Domain Name
+fullnameOverride: ""
+deploy:
+ # -- Intel Extension for Tensorflow Serving image
+ image: intel/intel-extension-for-tensorflow:serving-gpu
+ # -- Add Environment mapping
+ env:
+ configMapName: intel-proxy-config
+ enabled: true
+ # -- Model Name
+ modelName: ""
+ # -- Path to Model Folder
+ modelPath: /serving
+ # -- Number of pods
+ replicas: 1
+ resources:
+ # -- Maximum resources per pod
+ limits:
+ cpu: 4000m
+ memory: 1Gi
+ # -- Intel GPU Device Configuration
+ gpu.intel.com/i915: 1
+ # -- Minimum resources per pod
+ requests:
+ cpu: 1000m
+ memory: 512Mi
+ storage:
+ # -- Network File System (NFS) storage for models
+ nfs:
+ enabled: false
+ server: nil
+ path: nil
+ readOnly: true
+ subPath: nil
+service:
+ # -- Type of service
+ type: NodePort
+ # -- Port of the service
+ port: 9090
+pvc:
+ # -- Size of the storage
+ size: 1Gi
+ingress:
+ enabled: false
+ className: ""
+ annotations: {}
+ # kubernetes.io/ingress.class: nginx
+ # kubernetes.io/tls-acme: "true"
+ hosts:
+ - host: chart-example.local
+ paths:
+ - path: /
+ pathType: ImplementationSpecific
+ tls: []
+ # - secretName: chart-example-tls
+ # hosts:
+ # - chart-example.local
From 5cc2e18504ae2f38077ac95c83b8fc639651f05a Mon Sep 17 00:00:00 2001
From: tylertitsworth <tyler.titsworth@intel.com>
Date: Thu, 29 Aug 2024 14:52:15 -0700
Subject: [PATCH 2/3] val progress
Signed-off-by: tylertitsworth <tyler.titsworth@intel.com>
---
workflows/charts/tensorflow-serving/README.md | 15 +---
.../tensorflow-serving/templates/NOTES.txt | 11 +--
.../templates/deployment.yaml | 19 ++---
.../tensorflow-serving/templates/ingress.yaml | 75 -------------------
.../tensorflow-serving/templates/pvc.yaml | 29 +++++++
.../tensorflow-serving/templates/service.yaml | 9 ++-
.../templates/tests/test-connection.yaml | 10 +--
.../charts/tensorflow-serving/values.yaml | 23 +-----
.../tgi/templates/tests/test-connection.yaml | 2 +-
9 files changed, 60 insertions(+), 133 deletions(-)
delete mode 100644 workflows/charts/tensorflow-serving/templates/ingress.yaml
create mode 100644 workflows/charts/tensorflow-serving/templates/pvc.yaml
diff --git a/workflows/charts/tensorflow-serving/README.md b/workflows/charts/tensorflow-serving/README.md
index 853384ef..7961f3b8 100644
--- a/workflows/charts/tensorflow-serving/README.md
+++ b/workflows/charts/tensorflow-serving/README.md
@@ -17,23 +17,16 @@ TensorFlow Serving is a flexible, high-performance serving system for machine le
| deploy.env | object | `{"configMapName":"intel-proxy-config","enabled":true}` | Add Environment mapping |
| deploy.image | string | `"intel/intel-extension-for-tensorflow:serving-gpu"` | Intel Extension for Tensorflow Serving image |
| deploy.modelName | string | `""` | Model Name |
-| deploy.modelPath | string | `"/serving"` | Path to Model Folder |
| deploy.replicas | int | `1` | Number of pods |
| deploy.resources.limits | object | `{"cpu":"4000m","gpu.intel.com/i915":1,"memory":"1Gi"}` | Maximum resources per pod |
| deploy.resources.limits."gpu.intel.com/i915" | int | `1` | Intel GPU Device Configuration |
| deploy.resources.requests | object | `{"cpu":"1000m","memory":"512Mi"}` | Minimum resources per pod |
-| deploy.storage.nfs | object | `{"enabled":false,"path":"nil","readOnly":true,"server":"nil","subPath":"nil"}` | Network File System (NFS) storage for models |
+| deploy.storage.nfs | object | `{"enabled":false,"path":"nil","readOnly":true,"server":"nil"}` | Network File System (NFS) storage for models |
| fullnameOverride | string | `""` | Full qualified Domain Name |
-| ingress.annotations | object | `{}` | |
-| ingress.className | string | `""` | |
-| ingress.enabled | bool | `false` | |
-| ingress.hosts[0].host | string | `"chart-example.local"` | |
-| ingress.hosts[0].paths[0].path | string | `"/"` | |
-| ingress.hosts[0].paths[0].pathType | string | `"ImplementationSpecific"` | |
-| ingress.tls | list | `[]` | |
| nameOverride | string | `""` | Name of the serving service |
-| pvc.size | string | `"1Gi"` | Size of the storage |
-| service.port | int | `9090` | Port of the service |
+| pvc.size | string | `"5Gi"` | Size of the storage |
+| service.grpcPort | int | `8500` | |
+| service.restPort | int | `8501` | Port of the service |
| service.type | string | `"NodePort"` | Type of service |
----------------------------------------------
diff --git a/workflows/charts/tensorflow-serving/templates/NOTES.txt b/workflows/charts/tensorflow-serving/templates/NOTES.txt
index cbc436df..fb69969c 100644
--- a/workflows/charts/tensorflow-serving/templates/NOTES.txt
+++ b/workflows/charts/tensorflow-serving/templates/NOTES.txt
@@ -1,11 +1,5 @@
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 }}://{{ $host.host }}{{ .path }}
- {{- end }}
-{{- end }}
-{{- else if contains "NodePort" .Values.service.type }}
+{{- if contains "NodePort" .Values.service.type }}
export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "tensorflow-serving.fullname" . }})
export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
echo http://$NODE_IP:$NODE_PORT
@@ -20,3 +14,6 @@
echo "Visit http://127.0.0.1:8080 to use your application"
kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
{{- end }}
+2. Make a prediction
+ curl http://$NODE_IP:$NODE_PORT/v1/models/{{ .Values.deploy.modelName }}
+ curl -X POST http://$NODE_IP:$NODE_PORT/v1/models/{{ .Values.deploy.modelName }}:predict -d '{"data": []}'
diff --git a/workflows/charts/tensorflow-serving/templates/deployment.yaml b/workflows/charts/tensorflow-serving/templates/deployment.yaml
index e5d91b6c..0360fe4a 100644
--- a/workflows/charts/tensorflow-serving/templates/deployment.yaml
+++ b/workflows/charts/tensorflow-serving/templates/deployment.yaml
@@ -11,7 +11,8 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
-
+{{- $name := .Values.deploy.modelName | required ".Values.deploy.modelName is required." -}}
+---
apiVersion: apps/v1
kind: Deployment
metadata:
@@ -19,9 +20,7 @@ metadata:
labels:
{{- include "tensorflow-serving.labels" . | nindent 4 }}
spec:
- {{- if not .Values.autoscaling.enabled }}
replicas: {{ .Values.deploy.replicas }}
- {{- end }}
selector:
matchLabels:
{{- include "tensorflow-serving.selectorLabels" . | nindent 6 }}
@@ -44,21 +43,20 @@ spec:
env:
- name: MODEL_NAME
value: {{ .Values.deploy.modelName }}
- - name: MODEL_DIR
- value: {{ .Values.deploy.modelPath }}
ports:
- - name: serving
- containerPort: {{ .Values.service.port }}
+ - name: rest
+ containerPort: {{ .Values.service.restPort }}
+ - name: grpc
+ containerPort: {{ .Values.service.grpcPort }}
volumeMounts:
- mountPath: /dev/shm
name: dshm
{{- if .Values.deploy.storage.nfs.enabled }}
- name: model
- mountPath: /home/model-server/model-store
- subPath: {{ .Values.deploy.storage.nfs.subPath }}
+ mountPath: /models/{{ .Values.deploy.modelName }}
{{- else }}
- name: model
- mountPath: /home/model-server/model-store
+ mountPath: /models/{{ .Values.deploy.modelName }}
{{- end }}
resources:
{{- toYaml .Values.deploy.resources | nindent 12 }}
@@ -72,7 +70,6 @@ spec:
server: {{ .Values.deploy.storage.nfs.server }}
path: {{ .Values.deploy.storage.nfs.path }}
readOnly: {{ .Values.deploy.storage.nfs.readOnly }}
- emptyDir: {}
{{- else }}
- name: model
persistentVolumeClaim:
diff --git a/workflows/charts/tensorflow-serving/templates/ingress.yaml b/workflows/charts/tensorflow-serving/templates/ingress.yaml
deleted file mode 100644
index ac9bbc82..00000000
--- a/workflows/charts/tensorflow-serving/templates/ingress.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-# Copyright (c) 2024 Intel Corporation
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-{{- if .Values.ingress.enabled -}}
-{{- $fullName := include "tensorflow-serving.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 "tensorflow-serving.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 }}
diff --git a/workflows/charts/tensorflow-serving/templates/pvc.yaml b/workflows/charts/tensorflow-serving/templates/pvc.yaml
new file mode 100644
index 00000000..2cf9040d
--- /dev/null
+++ b/workflows/charts/tensorflow-serving/templates/pvc.yaml
@@ -0,0 +1,29 @@
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+---
+{{- if not .Values.deploy.storage.nfs.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+ name: {{ include "tensorflow-serving.fullname" . }}-model-dir
+ labels:
+ {{- include "tensorflow-serving.labels" . | nindent 4 }}
+spec:
+ accessModes:
+ - ReadWriteMany
+ resources:
+ requests:
+ storage: {{ .Values.pvc.size }}
+{{- end }}
diff --git a/workflows/charts/tensorflow-serving/templates/service.yaml b/workflows/charts/tensorflow-serving/templates/service.yaml
index d878b0c8..06f9131b 100644
--- a/workflows/charts/tensorflow-serving/templates/service.yaml
+++ b/workflows/charts/tensorflow-serving/templates/service.yaml
@@ -21,8 +21,11 @@ metadata:
spec:
type: {{ .Values.service.type }}
ports:
- - name: serving
- port: {{ .Values.service.port }}
- targetPort: serving
+ - name: rest
+ port: {{ .Values.service.restPort }}
+ targetPort: rest
+ - name: grpc
+ port: {{ .Values.service.grpcPort }}
+ targetPort: grpc
selector:
{{- include "tensorflow-serving.selectorLabels" . | nindent 4 }}
diff --git a/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
index 7914869c..0f17de24 100644
--- a/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
+++ b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
@@ -22,8 +22,8 @@ metadata:
"helm.sh/hook": test
spec:
containers:
- - name: wget
- image: busybox
- command: ['wget']
- args: ['{{ include "tensorflow-serving.fullname" . }}:{{ .Values.service.port }}']
- restartPolicy: Never
+ - name: info
+ image: curlimages/curl
+ command: ['sh', '-c']
+ args: ['curl -f {{ include "tensorflow-serving.fullname" . }}:{{ .Values.service.restPort }}/v1/model/{{ .Values.deploy.modelName}}']
+ restartPolicy: OnFailure
diff --git a/workflows/charts/tensorflow-serving/values.yaml b/workflows/charts/tensorflow-serving/values.yaml
index 4aef4120..e4b33284 100644
--- a/workflows/charts/tensorflow-serving/values.yaml
+++ b/workflows/charts/tensorflow-serving/values.yaml
@@ -25,8 +25,6 @@ deploy:
enabled: true
# -- Model Name
modelName: ""
- # -- Path to Model Folder
- modelPath: /serving
# -- Number of pods
replicas: 1
resources:
@@ -47,27 +45,12 @@ deploy:
server: nil
path: nil
readOnly: true
- subPath: nil
service:
# -- Type of service
type: NodePort
# -- Port of the service
- port: 9090
+ restPort: 8501
+ grpcPort: 8500
pvc:
# -- Size of the storage
- size: 1Gi
-ingress:
- enabled: false
- className: ""
- annotations: {}
- # kubernetes.io/ingress.class: nginx
- # kubernetes.io/tls-acme: "true"
- hosts:
- - host: chart-example.local
- paths:
- - path: /
- pathType: ImplementationSpecific
- tls: []
- # - secretName: chart-example-tls
- # hosts:
- # - chart-example.local
+ size: 5Gi
diff --git a/workflows/charts/tgi/templates/tests/test-connection.yaml b/workflows/charts/tgi/templates/tests/test-connection.yaml
index 113d8acf..007086c4 100644
--- a/workflows/charts/tgi/templates/tests/test-connection.yaml
+++ b/workflows/charts/tgi/templates/tests/test-connection.yaml
@@ -25,5 +25,5 @@ spec:
- name: info
image: curlimages/curl
command: ['sh', '-c']
- args: ['curl --noproxy "*" -f {{ include "tgi.fullname" . }}:{{ .Values.service.port }}/info']
+ args: ['curl -f {{ include "tgi.fullname" . }}:{{ .Values.service.port }}/info']
restartPolicy: OnFailure
From cc0c4633a043d57283bafce81fc7f4dd9e4f41e0 Mon Sep 17 00:00:00 2001
From: tylertitsworth <tyler.titsworth@intel.com>
Date: Tue, 3 Sep 2024 14:24:36 -0700
Subject: [PATCH 3/3] validate tf serving
Signed-off-by: tylertitsworth <tyler.titsworth@intel.com>
---
workflows/charts/tensorflow-serving/README.md | 2 --
.../tensorflow-serving/templates/deployment.yaml | 11 +++++++++--
.../charts/tensorflow-serving/templates/service.yaml | 4 ++--
.../templates/tests/test-connection.yaml | 2 +-
workflows/charts/tensorflow-serving/values.yaml | 3 ---
5 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/workflows/charts/tensorflow-serving/README.md b/workflows/charts/tensorflow-serving/README.md
index 7961f3b8..bfbb2900 100644
--- a/workflows/charts/tensorflow-serving/README.md
+++ b/workflows/charts/tensorflow-serving/README.md
@@ -25,8 +25,6 @@ TensorFlow Serving is a flexible, high-performance serving system for machine le
| fullnameOverride | string | `""` | Full qualified Domain Name |
| nameOverride | string | `""` | Name of the serving service |
| pvc.size | string | `"5Gi"` | Size of the storage |
-| service.grpcPort | int | `8500` | |
-| service.restPort | int | `8501` | Port of the service |
| service.type | string | `"NodePort"` | Type of service |
----------------------------------------------
diff --git a/workflows/charts/tensorflow-serving/templates/deployment.yaml b/workflows/charts/tensorflow-serving/templates/deployment.yaml
index 0360fe4a..e6a1fcf6 100644
--- a/workflows/charts/tensorflow-serving/templates/deployment.yaml
+++ b/workflows/charts/tensorflow-serving/templates/deployment.yaml
@@ -45,9 +45,16 @@ spec:
value: {{ .Values.deploy.modelName }}
ports:
- name: rest
- containerPort: {{ .Values.service.restPort }}
+ containerPort: 8500
+ protocol: TCP
- name: grpc
- containerPort: {{ .Values.service.grpcPort }}
+ containerPort: 8501
+ protocol: TCP
+ readinessProbe:
+ tcpSocket:
+ port: rest
+ initialDelay: 15
+ timeoutSeconds: 1
volumeMounts:
- mountPath: /dev/shm
name: dshm
diff --git a/workflows/charts/tensorflow-serving/templates/service.yaml b/workflows/charts/tensorflow-serving/templates/service.yaml
index 06f9131b..2eab7890 100644
--- a/workflows/charts/tensorflow-serving/templates/service.yaml
+++ b/workflows/charts/tensorflow-serving/templates/service.yaml
@@ -22,10 +22,10 @@ spec:
type: {{ .Values.service.type }}
ports:
- name: rest
- port: {{ .Values.service.restPort }}
+ port: 8500
targetPort: rest
- name: grpc
- port: {{ .Values.service.grpcPort }}
+ port: 8501
targetPort: grpc
selector:
{{- include "tensorflow-serving.selectorLabels" . | nindent 4 }}
diff --git a/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
index 0f17de24..0fe61c9a 100644
--- a/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
+++ b/workflows/charts/tensorflow-serving/templates/tests/test-connection.yaml
@@ -25,5 +25,5 @@ spec:
- name: info
image: curlimages/curl
command: ['sh', '-c']
- args: ['curl -f {{ include "tensorflow-serving.fullname" . }}:{{ .Values.service.restPort }}/v1/model/{{ .Values.deploy.modelName}}']
+ args: ['curl -f {{ include "tensorflow-serving.fullname" . }}:8501/v1/models/{{ .Values.deploy.modelName}}']
restartPolicy: OnFailure
diff --git a/workflows/charts/tensorflow-serving/values.yaml b/workflows/charts/tensorflow-serving/values.yaml
index e4b33284..39ed23af 100644
--- a/workflows/charts/tensorflow-serving/values.yaml
+++ b/workflows/charts/tensorflow-serving/values.yaml
@@ -48,9 +48,6 @@ deploy:
service:
# -- Type of service
type: NodePort
- # -- Port of the service
- restPort: 8501
- grpcPort: 8500
pvc:
# -- Size of the storage
size: 5Gi