kfserving

KFServing

KFServing provides a Kubernetes Custom Resource Definition for serving machine learning (ML) models on arbitrary frameworks. It aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX.

It encapsulates the complexity of autoscaling, networking, health checking, and server configuration to bring cutting edge serving features like GPU Autoscaling, Scale to Zero, and Canary Rollouts to your ML deployments. It enables a simple, pluggable, and complete story for Production ML Serving including prediction, pre-processing, post-processing and explainability. KFServing is being used across various organizations.

Architecture Review

Control Plane and Data Plane

Core Features and Examples

KFServing Features and Examples

Learn More

To learn more about KFServing, how to deploy it as part of Kubeflow, how to use various supported features, and how to participate in the KFServing community, please follow the KFServing docs on the Kubeflow Website. Additionally, we have compiled a list of KFServing presentations and demoes to dive through various details.

Prerequisites

Kubernetes 1.17 is the minimally recommended version, Knative Serving and Istio should be available on Kubernetes Cluster.

• Istio: v1.9.0+

  • KFServing currently only depends on Istio Ingress Gateway to route requests to inference services externally or internally. If you do not need Service Mesh, we recommend turning off Istio sidecar injection.

• Knative Serving: v0.19.0+

  • If you are running Service Mesh mode with Authorization please follow knative doc to setup the authorization policies.
  • If you are looking to use PodSpec fields such as nodeSelector, affinity or tolerations which are now supported in the KFServing v1beta1 API spec, you need to turn on the corresponding feature flags in your Knative configuration.

• Cert Manager: v1.3.0+

  • Cert manager is needed to provision KFServing webhook certs for production grade installation, alternatively you can run our self signed certs generation script.

Install KFServing

Standalone KFServing Installation

KFServing can be installed standalone if your kubernetes cluster meets the above prerequisites and KFServing controller is deployed in kfserving-system namespace.

TAG=v0.6.0

Install KFServing CRD and Controller

Due to a performance issue applying deeply nested CRDs, please ensure that your kubectl version fits into one of the following categories to ensure that you have the fix: >=1.16.14,<1.17.0 or >=1.17.11,<1.18.0 or >=1.18.8.

kubectl apply -f https://github.com/kubeflow/kfserving/releases/download/$TAG/kfserving.yaml

Standalone KFServing on OpenShift

To install standalone KFServing on OpenShift Container Platform, please follow the instructions here.

KFServing with Kubeflow Installation

KFServing is installed by default as part of Kubeflow installation and KFServing controller is deployed in kubeflow namespace.

⚠ Do ensure that you do not deploy InferenceService in kubeflow namespace which is labelled as control-plane and is system namespace.

Quick Install (On your local machine)

Make sure you have kubectl installed.

1. If you do not have an existing kubernetes cluster, you can create a quick kubernetes local cluster with kind.

Note that the minimal requirement for running KFServing is 4 cpus and 8Gi memory, so you need to change the docker resource setting to use 4 cpus and 8Gi memory.

kind create cluster

alternatively you can use Minikube

minikube start --cpus 4 --memory 8192

1. Install Istio lean version, Knative Serving, KFServing all in one.(this takes 30s)

./hack/quick_install.sh

Setup Ingress Gateway

If the default ingress gateway setup does not fit your need, you can choose to setup a custom ingress gateway

• Configure Custom Ingress Gateway
  • In addition you need to update KFServing configmap to use the custom ingress gateway.
• Configure Custom Domain
• Configure HTTPS Connection

Determine the ingress IP and ports

Execute the following command to determine if your kubernetes cluster is running in an environment that supports external load balancers

$ kubectl get svc istio-ingressgateway -n istio-system
NAME                   TYPE           CLUSTER-IP       EXTERNAL-IP      PORT(S)   AGE
istio-ingressgateway   LoadBalancer   172.21.109.129   130.211.10.121   ...       17h

If the EXTERNAL-IP value is set, your environment has an external load balancer that you can use for the ingress gateway.

export INGRESS_HOST=$(kubectl -n istio-system get service istio-ingressgateway -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
export INGRESS_PORT=$(kubectl -n istio-system get service istio-ingressgateway -o jsonpath='{.spec.ports[?(@.name=="http2")].port}')

If the EXTERNAL-IP value is none (or perpetually pending), your environment does not provide an external load balancer for the ingress gateway. In this case, you can access the gateway using the service’s node port.

# GKE
export INGRESS_HOST=worker-node-address
# Minikube
export INGRESS_HOST=$(minikube ip)
# Other environment(On Prem)
export INGRESS_HOST=$(kubectl get po -l istio=ingressgateway -n istio-system -o jsonpath='{.items[0].status.hostIP}')

export INGRESS_PORT=$(kubectl -n istio-system get service istio-ingressgateway -o jsonpath='{.spec.ports[?(@.name=="http2")].nodePort}')

Alternatively you can do Port Forward for testing purpose

INGRESS_GATEWAY_SERVICE=$(kubectl get svc --namespace istio-system --selector="app=istio-ingressgateway" --output jsonpath='{.items[0].metadata.name}')
kubectl port-forward --namespace istio-system svc/${INGRESS_GATEWAY_SERVICE} 8080:80
# start another terminal
export INGRESS_HOST=localhost
export INGRESS_PORT=8080

Test KFServing Installation

kubectl get po -n kfserving-system
NAME                             READY   STATUS    RESTARTS   AGE
kfserving-controller-manager-0   2/2     Running   2          13m

API_VERSION=v1beta1
kubectl create namespace kfserving-test
kubectl apply -f docs/samples/${API_VERSION}/sklearn/v1/sklearn.yaml -n kfserving-test

kubectl get inferenceservices sklearn-iris -n kfserving-test
NAME           URL                                                 READY   PREV   LATEST   PREVROLLEDOUTREVISION   LATESTREADYREVISION                    AGE
sklearn-iris   http://sklearn-iris.kfserving-test.example.com      True           100                              sklearn-iris-predictor-default-47q2g   7d23h

curl -v http://sklearn-iris.kfserving-test.${CUSTOM_DOMAIN}/v1/models/sklearn-iris:predict -d @./docs/samples/${API_VERSION}/sklearn/v1/iris-input.json

kubectl get svc istio-ingressgateway --namespace istio-system

NAME                   TYPE           CLUSTER-IP     EXTERNAL-IP      PORT(S)                                                                                                                                      AGE
istio-ingressgateway   LoadBalancer   10.51.253.94   35.237.217.209

kubectl edit cm config-domain --namespace knative-serving

curl -v http://sklearn-iris.kfserving-test.35.237.217.209.xip.io/v1/models/sklearn-iris:predict -d @./docs/samples/${API_VERSION}/sklearn/v1/iris-input.json

SERVICE_HOSTNAME=$(kubectl get inferenceservice sklearn-iris -n kfserving-test -o jsonpath='{.status.url}' | cut -d "/" -f 3)
curl -v -H "Host: ${SERVICE_HOSTNAME}" http://${INGRESS_HOST}:${INGRESS_PORT}/v1/models/sklearn-iris:predict -d @./docs/samples/${API_VERSION}/sklearn/v1/iris-input.json

curl -v http://sklearn-iris.kfserving-test/v1/models/sklearn-iris:predict -d @./docs/samples/${API_VERSION}/sklearn/v1/iris-input.json

# use kubectl create instead of apply because the job template is using generateName which doesn't work with kubectl apply
kubectl create -f docs/samples/${API_VERSION}/sklearn/v1/perf.yaml -n kfserving-test
# wait the job to be done and check the log
kubectl logs load-test8b58n-rgfxr -n kfserving-test
Requests      [total, rate, throughput]         30000, 500.02, 499.99
Duration      [total, attack, wait]             1m0s, 59.998s, 3.336ms
Latencies     [min, mean, 50, 90, 95, 99, max]  1.743ms, 2.748ms, 2.494ms, 3.363ms, 4.091ms, 7.749ms, 46.354ms
Bytes In      [total, mean]                     690000, 23.00
Bytes Out     [total, mean]                     2460000, 82.00
Success       [ratio]                           100.00%
Status Codes  [code:count]                      200:30000
Error Set:

Setup Monitoring

• Prometheus based monitoring for KFServing
• Metrics driven automated rollouts using Iter8
• Dashboard for ServiceMesh

Use KFServing SDK

• Install the SDK

  pip install kfserving
  

• Check the KFServing SDK documents from here.

• Follow the example(s) here to use the KFServing SDK to create, rollout, promote, and delete an InferenceService instance.

KFServing Presentations and Demoes

KFServing Presentations and Demoes

KFServing Roadmap

KFServing Roadmap

KFServing API Reference

KFServing v1alpha2 API Docs

KFServing v1beta1 API Docs

KFServing Debugging Guide ⭐

Debug KFServing InferenceService

Developer Guide

Developer Guide.

Performance Tests

KFServing benchmark test comparing Knative and Kubernetes Deployment with HPA

Contributor Guide

Contributor Guide

KFServing Adopters

KFServing Adopters