Deployment to AKS uses old image

I'm trying to update an endpoint, that is already deployed at AKS. Here is my workflow:
1. I'm updating a custom image - e.g. update installed libraries. It is registered in private ACR.
2. I call environment.build() - forcing an azureml image to be rebuilt, so that changes in source image will be updated in final image. Please notice, that the built image has the same name: `d2bbe17668204c4f957f17cca62a7db4.azurecr.io/azureml/azureml_02fba29521dca17addff8c3b5f3d93cb`. The only thing that changes is the source docker, which is reflected with a new manifest.
3. Deployment of the new model:
`webservice = Model.deploy(
workspace=ws,
name=service_name,
models=[model],
inference_config=inference_config,
deployment_config=deployment_config,
show_output=True,
overwrite=True
)`

Deployment goes well, however the app runs on the previous image.
In the ACR the latest version is:
`d2bbe17668204c4f957f17cca62a7db4.azurecr.io/azureml/azureml_02fba29521dca17addff8c3b5f3d93cb:latest`
and `sha256:19b9c6dfaa3cd0ad4364719fcdf2a170606b9e43106225748f6785291c43d7f4`
while if I describe a pod in K8 it uses the previous version from cache:
`d2bbe17668204c4f957f17cca62a7db4.azurecr.io/azureml/azureml_02fba29521dca17addff8c3b5f3d93cb@sha256:bc7911cd9109ea3748feba3a56b1f8f8bc8c65b154d75a54bf96b87d80b5e472`
I think that's due to imagePullPolicy: IfNotPresent.
In the kubernetes describe pod I can see, that an image was not pulled but used from cache instead.
I couldn't find any way to change this setting to Always.
I have patched the deployment map and correct image has been pulled, so I know that this option ("Always") would fix this issue for me. Thanks for any help!

Commencez par le workflow Model.deploy et la description du pod AKS, en comparant les digests d’image ACR et la imagePullPolicy du déploiement. Confirmez comment le déploiement Azure Machine Learning spécifie son comportement de récupération d’image ; le travail est considéré comme terminé lorsqu’un redéploiement récupère l’image ACR actuelle au lieu d’utiliser le digest mis en cache.

Rédigé par le modèle d'indexation à partir du texte de l'issue.