SlideShare ist ein Scribd-Unternehmen logo
1 von 9
Downloaden Sie, um offline zu lesen
Kubeflow Pipelines component
for KFServing
Animesh Singh, Paul Van Eck
Kubeflow Pipelines
•Pre-built components: Just provide params or code snippets
(e.g. training code)
•Create your own components from code or libraries
•Use any runtime, framework, data types
•Attach k8s objects - volumes, secrets
Containerized implementations of ML Tasks
•Specified via Python DSL
•Inferred from data dependencies on input/output
Specification of the sequence of steps
•A “Run” = Pipeline invoked w/ specific parameters
•Can be cloned with different parameters
Input Parameters
•Invoke a single run or create a recurring scheduled pipeline
Schedules
KFServing Component
● Allows usage of KFServing
within a Kubeflow pipeline.
● Uses KFServing Python
package (v0.5.1) and v1beta1
API.
● Can easily deploy
InferenceServices and perform
canary rollouts.
● Supports passing in raw
InferenceService YAML
● Source Code
Sample Usage
import kfp
kfserving_op =
kfp.components.load_component_from_url('.../kfserving/component.yaml')
@dsl.pipeline(
name='KFServing Pipeline',
description='Pipeline for KFServing.'
)
def kfserving_pipeline():
kfserving_op(
action='apply',
model_name='tf-sample',
model_uri='gs://kfserving-samples/models/tensorflow/flowers',
framework='tensorflow',
)
kfp.Client().create_run_from_pipeline_func(
kfserving_pipeline,
arguments={}
)
Deploy a TensorFlow model
Kubeflow Pipelines can train, deploy and serve
5
Open Source Dojo
More use cases!
Analysis
● Pipeline components rely on passing in
specific args to some CLI program.
● The primary support is for predictors with
limited customization options.
● KFServing supports many PodSpec fields
that aren’t first-class component
arguments.
● Transformers and explainers are also not
first class.
Analysis
● Users can still deploy InferenceServices
with full customizability by passing the
component their YAML definitions.
○ All PodSpec fields.
○ Transformers/Explainers.
○ Specific annotations/labels.
● This is the most flexible format.
○ Perhaps this should be the recommended way?
○ Offers format consistency compared with
kubectl/KFServing interactions.
isvc_yaml = '''
apiVersion: serving.kubeflow.org/v1beta1
kind: InferenceService
metadata:
name: torchserve-transformer
spec:
transformer:
containers:
- image: kfserving/torchserve-image-transformer:latest
name: kfserving-container
predictor:
nodeSelector:
disktype: ssd
pytorch:
storageUri: gs://torchserve/image_classifier
'''
kfserving_op(
action='apply',
inferenceservice_yaml=isvc_yaml
)
KFServing-Pipeline Demo

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Introducing Kubeflow (w. Special Guests Tensorflow and Apache Spark)
Introducing Kubeflow (w. Special Guests Tensorflow and Apache Spark)Introducing Kubeflow (w. Special Guests Tensorflow and Apache Spark)
Introducing Kubeflow (w. Special Guests Tensorflow and Apache Spark)
 
Introduction to Kubernetes RBAC
Introduction to Kubernetes RBACIntroduction to Kubernetes RBAC
Introduction to Kubernetes RBAC
 
Kubeflow at Spotify (For the Kubeflow Summit)
Kubeflow at Spotify (For the Kubeflow Summit)Kubeflow at Spotify (For the Kubeflow Summit)
Kubeflow at Spotify (For the Kubeflow Summit)
 
Kubernetes & Google Kubernetes Engine (GKE)
Kubernetes & Google Kubernetes Engine (GKE)Kubernetes & Google Kubernetes Engine (GKE)
Kubernetes & Google Kubernetes Engine (GKE)
 
Kubernetes Helm: Why It Matters
Kubernetes Helm: Why It MattersKubernetes Helm: Why It Matters
Kubernetes Helm: Why It Matters
 
User authentication and authorizarion in Kubernetes
User authentication and authorizarion in KubernetesUser authentication and authorizarion in Kubernetes
User authentication and authorizarion in Kubernetes
 
CI/CD Tools Universe: The Ultimate List
CI/CD Tools Universe: The Ultimate ListCI/CD Tools Universe: The Ultimate List
CI/CD Tools Universe: The Ultimate List
 
Service Mesh with Apache Kafka, Kubernetes, Envoy, Istio and Linkerd
Service Mesh with Apache Kafka, Kubernetes, Envoy, Istio and LinkerdService Mesh with Apache Kafka, Kubernetes, Envoy, Istio and Linkerd
Service Mesh with Apache Kafka, Kubernetes, Envoy, Istio and Linkerd
 
Drifting Away: Testing ML Models in Production
Drifting Away: Testing ML Models in ProductionDrifting Away: Testing ML Models in Production
Drifting Away: Testing ML Models in Production
 
[OpenInfra Days Korea 2018] (Track 4) - Grafana를 이용한 OpenStack 클라우드 성능 모니터링
[OpenInfra Days Korea 2018] (Track 4) - Grafana를 이용한 OpenStack 클라우드 성능 모니터링[OpenInfra Days Korea 2018] (Track 4) - Grafana를 이용한 OpenStack 클라우드 성능 모니터링
[OpenInfra Days Korea 2018] (Track 4) - Grafana를 이용한 OpenStack 클라우드 성능 모니터링
 
K8s in 3h - Kubernetes Fundamentals Training
K8s in 3h - Kubernetes Fundamentals TrainingK8s in 3h - Kubernetes Fundamentals Training
K8s in 3h - Kubernetes Fundamentals Training
 
MLflow Model Serving
MLflow Model ServingMLflow Model Serving
MLflow Model Serving
 
KEDA Overview
KEDA OverviewKEDA Overview
KEDA Overview
 
Deep dive into Kubernetes Networking
Deep dive into Kubernetes NetworkingDeep dive into Kubernetes Networking
Deep dive into Kubernetes Networking
 
Machine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta LakeMachine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta Lake
 
Replacing iptables with eBPF in Kubernetes with Cilium
Replacing iptables with eBPF in Kubernetes with CiliumReplacing iptables with eBPF in Kubernetes with Cilium
Replacing iptables with eBPF in Kubernetes with Cilium
 
How API Enablement Drives Legacy Modernization
How API Enablement Drives Legacy ModernizationHow API Enablement Drives Legacy Modernization
How API Enablement Drives Legacy Modernization
 
Introduction to MLflow
Introduction to MLflowIntroduction to MLflow
Introduction to MLflow
 
Workday's Next Generation Private Cloud
Workday's Next Generation Private CloudWorkday's Next Generation Private Cloud
Workday's Next Generation Private Cloud
 
MLOps with Kubeflow
MLOps with Kubeflow MLOps with Kubeflow
MLOps with Kubeflow
 

Ähnlich wie KFServing and Kubeflow Pipelines

Ähnlich wie KFServing and Kubeflow Pipelines (20)

ASP.NET vNext
ASP.NET vNextASP.NET vNext
ASP.NET vNext
 
DEVNET-1166 Open SDN Controller APIs
DEVNET-1166	Open SDN Controller APIsDEVNET-1166	Open SDN Controller APIs
DEVNET-1166 Open SDN Controller APIs
 
Distributed & Highly Available server applications in Java and Scala
Distributed & Highly Available server applications in Java and ScalaDistributed & Highly Available server applications in Java and Scala
Distributed & Highly Available server applications in Java and Scala
 
Kubernetes Internals
Kubernetes InternalsKubernetes Internals
Kubernetes Internals
 
Deploy your machine learning models to production with Kubernetes
Deploy your machine learning models to production with KubernetesDeploy your machine learning models to production with Kubernetes
Deploy your machine learning models to production with Kubernetes
 
Pipelines for model deployment
Pipelines for model deploymentPipelines for model deployment
Pipelines for model deployment
 
Real-time Streaming Pipelines with FLaNK
Real-time Streaming Pipelines with FLaNKReal-time Streaming Pipelines with FLaNK
Real-time Streaming Pipelines with FLaNK
 
18th Athens Big Data Meetup - 2nd Talk - Run Spark and Flink Jobs on Kubernetes
18th Athens Big Data Meetup - 2nd Talk - Run Spark and Flink Jobs on Kubernetes18th Athens Big Data Meetup - 2nd Talk - Run Spark and Flink Jobs on Kubernetes
18th Athens Big Data Meetup - 2nd Talk - Run Spark and Flink Jobs on Kubernetes
 
KSQL---Streaming SQL for Apache Kafka
KSQL---Streaming SQL for Apache KafkaKSQL---Streaming SQL for Apache Kafka
KSQL---Streaming SQL for Apache Kafka
 
eCAP Developer Walkthru
eCAP Developer WalkthrueCAP Developer Walkthru
eCAP Developer Walkthru
 
Containerized architectures for deep learning
Containerized architectures for deep learningContainerized architectures for deep learning
Containerized architectures for deep learning
 
Manchester MuleSoft Meetup #6 - Runtime Fabric with Mulesoft
Manchester MuleSoft Meetup #6 - Runtime Fabric with Mulesoft Manchester MuleSoft Meetup #6 - Runtime Fabric with Mulesoft
Manchester MuleSoft Meetup #6 - Runtime Fabric with Mulesoft
 
.NET Core: a new .NET Platform
.NET Core: a new .NET Platform.NET Core: a new .NET Platform
.NET Core: a new .NET Platform
 
ApacheCon NA - Apache Camel K: connect your Knative serverless applications w...
ApacheCon NA - Apache Camel K: connect your Knative serverless applications w...ApacheCon NA - Apache Camel K: connect your Knative serverless applications w...
ApacheCon NA - Apache Camel K: connect your Knative serverless applications w...
 
01 - VMUGIT - Lecce 2018 - Fabio Rapposelli, VMware
01 - VMUGIT - Lecce 2018 - Fabio Rapposelli, VMware01 - VMUGIT - Lecce 2018 - Fabio Rapposelli, VMware
01 - VMUGIT - Lecce 2018 - Fabio Rapposelli, VMware
 
Jug - ecosystem
Jug -  ecosystemJug -  ecosystem
Jug - ecosystem
 
Kubernetes fundamentals
Kubernetes fundamentalsKubernetes fundamentals
Kubernetes fundamentals
 
Chti jug - 2018-06-26
Chti jug - 2018-06-26Chti jug - 2018-06-26
Chti jug - 2018-06-26
 
Setup Kubernetes Cluster On AWS Using KOPS
Setup Kubernetes Cluster On AWS Using KOPSSetup Kubernetes Cluster On AWS Using KOPS
Setup Kubernetes Cluster On AWS Using KOPS
 
A Primer Towards Running Kafka on Top of Kubernetes.pdf
A Primer Towards Running Kafka on Top of Kubernetes.pdfA Primer Towards Running Kafka on Top of Kubernetes.pdf
A Primer Towards Running Kafka on Top of Kubernetes.pdf
 

Mehr von Animesh Singh

Building a PaaS Platform like Bluemix on OpenStack
Building a PaaS Platform like Bluemix on OpenStackBuilding a PaaS Platform like Bluemix on OpenStack
Building a PaaS Platform like Bluemix on OpenStack
Animesh Singh
 
Automated Lifecycle Management - CloudFoundry on OpenStack
Automated Lifecycle Management - CloudFoundry on OpenStackAutomated Lifecycle Management - CloudFoundry on OpenStack
Automated Lifecycle Management - CloudFoundry on OpenStack
Animesh Singh
 

Mehr von Animesh Singh (20)

Machine Learning Exchange (MLX)
Machine Learning Exchange (MLX)Machine Learning Exchange (MLX)
Machine Learning Exchange (MLX)
 
KFServing Payload Logging for Trusted AI
KFServing Payload Logging for Trusted AIKFServing Payload Logging for Trusted AI
KFServing Payload Logging for Trusted AI
 
KFServing and Feast
KFServing and FeastKFServing and Feast
KFServing and Feast
 
Defend against adversarial AI using Adversarial Robustness Toolbox
Defend against adversarial AI using Adversarial Robustness Toolbox Defend against adversarial AI using Adversarial Robustness Toolbox
Defend against adversarial AI using Adversarial Robustness Toolbox
 
Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]
Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]
Hybrid Cloud, Kubeflow and Tensorflow Extended [TFX]
 
Trusted, Transparent and Fair AI using Open Source
Trusted, Transparent and Fair AI using Open SourceTrusted, Transparent and Fair AI using Open Source
Trusted, Transparent and Fair AI using Open Source
 
AIF360 - Trusted and Fair AI
AIF360 - Trusted and Fair AIAIF360 - Trusted and Fair AI
AIF360 - Trusted and Fair AI
 
AI & Machine Learning Pipelines with Knative
AI & Machine Learning Pipelines with KnativeAI & Machine Learning Pipelines with Knative
AI & Machine Learning Pipelines with Knative
 
Fabric for Deep Learning
Fabric for Deep LearningFabric for Deep Learning
Fabric for Deep Learning
 
Microservices, Kubernetes and Istio - A Great Fit!
Microservices, Kubernetes and Istio - A Great Fit!Microservices, Kubernetes and Istio - A Great Fit!
Microservices, Kubernetes and Istio - A Great Fit!
 
How to build a Distributed Serverless Polyglot Microservices IoT Platform us...
How to build a Distributed Serverless Polyglot Microservices IoT Platform us...How to build a Distributed Serverless Polyglot Microservices IoT Platform us...
How to build a Distributed Serverless Polyglot Microservices IoT Platform us...
 
How to build an event-driven, polyglot serverless microservices framework on ...
How to build an event-driven, polyglot serverless microservices framework on ...How to build an event-driven, polyglot serverless microservices framework on ...
How to build an event-driven, polyglot serverless microservices framework on ...
 
As a Service: Cloud Foundry on OpenStack - Lessons Learnt
As a Service: Cloud Foundry on OpenStack - Lessons LearntAs a Service: Cloud Foundry on OpenStack - Lessons Learnt
As a Service: Cloud Foundry on OpenStack - Lessons Learnt
 
Introducing Cloud Native, Event Driven, Serverless, Micrsoservices Framework ...
Introducing Cloud Native, Event Driven, Serverless, Micrsoservices Framework ...Introducing Cloud Native, Event Driven, Serverless, Micrsoservices Framework ...
Introducing Cloud Native, Event Driven, Serverless, Micrsoservices Framework ...
 
Finding and-organizing Great Cloud Foundry User Groups
Finding and-organizing Great Cloud Foundry User GroupsFinding and-organizing Great Cloud Foundry User Groups
Finding and-organizing Great Cloud Foundry User Groups
 
CAPS: What's best for deploying and managing OpenStack? Chef vs. Ansible vs. ...
CAPS: What's best for deploying and managing OpenStack? Chef vs. Ansible vs. ...CAPS: What's best for deploying and managing OpenStack? Chef vs. Ansible vs. ...
CAPS: What's best for deploying and managing OpenStack? Chef vs. Ansible vs. ...
 
Building a PaaS Platform like Bluemix on OpenStack
Building a PaaS Platform like Bluemix on OpenStackBuilding a PaaS Platform like Bluemix on OpenStack
Building a PaaS Platform like Bluemix on OpenStack
 
Cloud foundry Docker Openstack - Leading Open Source Triumvirate
Cloud foundry Docker Openstack - Leading Open Source TriumvirateCloud foundry Docker Openstack - Leading Open Source Triumvirate
Cloud foundry Docker Openstack - Leading Open Source Triumvirate
 
Build Scalable Internet of Things Apps using Cloud Foundry, Bluemix & Cloudant
Build Scalable Internet of Things Apps using Cloud Foundry, Bluemix & CloudantBuild Scalable Internet of Things Apps using Cloud Foundry, Bluemix & Cloudant
Build Scalable Internet of Things Apps using Cloud Foundry, Bluemix & Cloudant
 
Automated Lifecycle Management - CloudFoundry on OpenStack
Automated Lifecycle Management - CloudFoundry on OpenStackAutomated Lifecycle Management - CloudFoundry on OpenStack
Automated Lifecycle Management - CloudFoundry on OpenStack
 

Kürzlich hochgeladen

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Kürzlich hochgeladen (20)

Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 

KFServing and Kubeflow Pipelines

  • 1. Kubeflow Pipelines component for KFServing Animesh Singh, Paul Van Eck
  • 2. Kubeflow Pipelines •Pre-built components: Just provide params or code snippets (e.g. training code) •Create your own components from code or libraries •Use any runtime, framework, data types •Attach k8s objects - volumes, secrets Containerized implementations of ML Tasks •Specified via Python DSL •Inferred from data dependencies on input/output Specification of the sequence of steps •A “Run” = Pipeline invoked w/ specific parameters •Can be cloned with different parameters Input Parameters •Invoke a single run or create a recurring scheduled pipeline Schedules
  • 3. KFServing Component ● Allows usage of KFServing within a Kubeflow pipeline. ● Uses KFServing Python package (v0.5.1) and v1beta1 API. ● Can easily deploy InferenceServices and perform canary rollouts. ● Supports passing in raw InferenceService YAML ● Source Code
  • 4. Sample Usage import kfp kfserving_op = kfp.components.load_component_from_url('.../kfserving/component.yaml') @dsl.pipeline( name='KFServing Pipeline', description='Pipeline for KFServing.' ) def kfserving_pipeline(): kfserving_op( action='apply', model_name='tf-sample', model_uri='gs://kfserving-samples/models/tensorflow/flowers', framework='tensorflow', ) kfp.Client().create_run_from_pipeline_func( kfserving_pipeline, arguments={} ) Deploy a TensorFlow model
  • 5. Kubeflow Pipelines can train, deploy and serve 5 Open Source Dojo
  • 7. Analysis ● Pipeline components rely on passing in specific args to some CLI program. ● The primary support is for predictors with limited customization options. ● KFServing supports many PodSpec fields that aren’t first-class component arguments. ● Transformers and explainers are also not first class.
  • 8. Analysis ● Users can still deploy InferenceServices with full customizability by passing the component their YAML definitions. ○ All PodSpec fields. ○ Transformers/Explainers. ○ Specific annotations/labels. ● This is the most flexible format. ○ Perhaps this should be the recommended way? ○ Offers format consistency compared with kubectl/KFServing interactions. isvc_yaml = ''' apiVersion: serving.kubeflow.org/v1beta1 kind: InferenceService metadata: name: torchserve-transformer spec: transformer: containers: - image: kfserving/torchserve-image-transformer:latest name: kfserving-container predictor: nodeSelector: disktype: ssd pytorch: storageUri: gs://torchserve/image_classifier ''' kfserving_op( action='apply', inferenceservice_yaml=isvc_yaml )