Closed lampajr closed 9 months ago
As first iteration I was able to create a custom storage initializer that interacts with the deployed model registry, this was we could create InferenceService
using a custom storageUri
with a model registry specific format like model-registry://
.
Created https://github.com/lampajr/model-registry-storage-initializer that showcase the usage of the initializer with a simple Quickstart based on a plain Kserve
installation.
Next step: try to demonstrate the integration with the ODH platform.
I generalized the implementation of this custom storage initializer to make usage of the model registry REST interface such that any model registry (which is compliant with the openapi spec) is suitable to be adopted.
Keeping track of this exploration on Kserve repo as well: https://github.com/kserve/kserve/issues/3343
Additional findings:
modelmesh-serving
to keep track of this.As I the feasibility on Kserve side is proven using the created custom storage initializer image I would close this issue as the exploration/experimentation can be considered succeeded for now.
Opened a different issue for the ModelMesh exploration Created issue to further investigate similar enhancement for ModelMesh deployments https://github.com/opendatahub-io/model-registry/issues/262
Investigate/explore the
ClusterStorageContainer
capability that kserve introduced in the latest release.Idea behind this exploration:
storage-initializer
that will match URI format likemodel-registry://
[1]InferenceService
that will use model registry could be something like (already supported by kserve):[1] https://kserve.github.io/website/latest/modelserving/storage/storagecontainers/