fedora@ip-172-31-37-101:~$ git clone https://github.com/neuralmagic/gateway-api-inference-extension.git
cd gateway-api-inference-extension
Cloning into 'gateway-api-inference-extension'...
remote: Enumerating objects: 5757, done.
remote: Counting objects: 100% (1395/1395), done.
remote: Compressing objects: 100% (318/318), done.
remote: Total 5757 (delta 1188), reused 1078 (delta 1077), pack-reused 4362 (from 3)
Receiving objects: 100% (5757/5757), 7.04 MiB | 38.35 MiB/s, done.
Resolving deltas: 100% (3112/3112), done.
fedora@ip-172-31-37-101:~$ cd gateway-api-inference-extension
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -k "github.com/kubernetes-sigs/gateway-api/config/crd?ref=v1.2.1"
customresourcedefinition.apiextensions.k8s.io/gatewayclasses.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/gateways.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/grpcroutes.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/httproutes.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/referencegrants.gateway.networking.k8s.io configured
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -k deploy/components/crds-gateway-api
customresourcedefinition.apiextensions.k8s.io/gatewayclasses.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/gateways.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/grpcroutes.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/httproutes.gateway.networking.k8s.io configured
customresourcedefinition.apiextensions.k8s.io/referencegrants.gateway.networking.k8s.io configured
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl api-versions | grep "gateway.networking.k8s.io"
gateway.networking.k8s.io/v1
gateway.networking.k8s.io/v1beta1
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -f config/crd/bases/inference.networking.x-k8s.io_inferencepools.yaml
kubectl apply -f config/crd/bases/inference.networking.x-k8s.io_inferencemodels.yaml
customresourcedefinition.apiextensions.k8s.io/inferencepools.inference.networking.x-k8s.io created
customresourcedefinition.apiextensions.k8s.io/inferencemodels.inference.networking.x-k8s.io created
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -k config/crd
customresourcedefinition.apiextensions.k8s.io/inferencemodels.inference.networking.x-k8s.io unchanged
customresourcedefinition.apiextensions.k8s.io/inferencepools.inference.networking.x-k8s.io unchanged
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -k "github.com/neuralmagic/gateway-api-inference-extension//config/crd?ref=dev"
customresourcedefinition.apiextensions.k8s.io/inferencemodels.inference.networking.x-k8s.io unchanged
customresourcedefinition.apiextensions.k8s.io/inferencepools.inference.networking.x-k8s.io unchanged
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl api-versions | grep "inference.networking.x-k8s.io"
inference.networking.x-k8s.io/v1alpha2
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ helm upgrade -i \
kgateway-crds \
oci://cr.kgateway.dev/kgateway-dev/charts/kgateway-crds \
--version v2.0.0 \
--namespace kgateway-system \
--create-namespace
Release "kgateway-crds" does not exist. Installing it now.
Pulled: cr.kgateway.dev/kgateway-dev/charts/kgateway-crds:v2.0.0
Digest: sha256:b405a0fbca50ae816bba355f1133cb456f280d9925d824166b7b6fc4e96f2077
NAME: kgateway-crds
LAST DEPLOYED: Sat Apr 26 04:19:15 2025
NAMESPACE: kgateway-system
STATUS: deployed
REVISION: 1
TEST SUITE: None
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl api-versions | grep "gateway.kgateway.dev"
gateway.kgateway.dev/v1alpha1
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ helm upgrade -i \
kgateway \
oci://cr.kgateway.dev/kgateway-dev/charts/kgateway \
--version v2.0.0 \
--namespace kgateway-system \
--create-namespace \
--set inferenceExtension.enabled=true \
--set securityContext.allowPrivilegeEscalation=false \
--set securityContext.capabilities.drop={ALL} \
--set podSecurityContext.seccompProfile.type=RuntimeDefault \
--set podSecurityContext.runAsNonRoot=true
Release "kgateway" does not exist. Installing it now.
Pulled: cr.kgateway.dev/kgateway-dev/charts/kgateway:v2.0.0
Digest: sha256:bbd7559eaa05ef6c27382390768889f5475e75bdcb4bd81ebd0f770cd14ab7a8
NAME: kgateway
LAST DEPLOYED: Sat Apr 26 04:19:29 2025
NAMESPACE: kgateway-system
STATUS: deployed
REVISION: 1
TEST SUITE: None
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl get pods -n kgateway-system
NAME READY STATUS RESTARTS AGE
kgateway-7c58ddd989-8lsml 1/1 Running 0 35s
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl apply -f gateway.yaml
kubectl apply -f gatewayparameters.yaml
gateway.gateway.networking.k8s.io/inference-gateway created
gatewayparameters.gateway.kgateway.dev/custom-gw-params created
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$
fedora@ip-172-31-37-101:~/gateway-api-inference-extension$ kubectl get gateway
NAME CLASS ADDRESS PROGRAMMED AGE
inference-gateway kgateway 172.30.123.225 True 6s
Created
April 26, 2025 04:30
-
-
Save nerdalert/3fddc640be121d946cf97b7456e5c3cf to your computer and use it in GitHub Desktop.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment