mirror of
https://github.com/helm/charts.git
synced 2026-08-23 22:37:45 +00:00
cheyang
d4aff856e8
* [incubator/tensorflow-serving] generic tensorflow model server support fix according to review comments support when not having pvc, make the e2e testing pass helm create with 2.8.1 * fix app name * make port not configurable * add named port * move to stable * update named port in service * add named port to tcp check * fix reference to stable
9 lines
688 B
Plaintext
9 lines
688 B
Plaintext
Getting Started:
|
|
|
|
**** NOTE: It may take a few minutes for the LoadBalancer IP to be available. ****
|
|
**** You can watch the status of by running 'kubectl get svc --namespace {{ .Release.Namespace }} -w {{ template "tensorflow-serving.fullname" . }}' ****
|
|
export TF_SERVING_SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ template "tensorflow-serving.fullname" . }} -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
|
|
echo docker run -it --rm cheyang/tf-mnist:grpcio_upgraded /serving/bazel-bin/tensorflow_serving/example/mnist_client --num_tests=1000 --server=$TF_SERVING_SERVICE_IP:9090`
|
|
|
|
|