What is the best way to multi model serving on local storage?

[HyeongminMoon]

I executed Kserve successfully with my custom pytorch model(custom torchserve image) and local storage(PVC).

And I am trying to run multi model serving with same above environments, but I found current model-mesh only supports S3-based storage.

1. Is there any method to open model-mesh with local storage now?
2. If not, What is the best way to multi model serving on local storage(without model-mesh, such as using many InferenceServices?)

This is my settings:

• Container: custom container based on torchserve-kfs:0.5.3-gpu
• Storage: PVC
• Model: MAR file from my custom pytorch model
• Kserve==0.8.0

I need your help! Thanks!

[bredamatt]

For this I'd recommend setting up local storage that is S3 compatible like Minio 👍🏼