This article provides an overview of improvements in the Fortanix Confidential AI 3.19 release.
- This release adds pagination support for the Confidential AI workflows list.
- This release provides some improvements to the Confidential AI Inference form, where the following are the sequence of steps for inference:
- A model is selected first. This can be either (1) a trained model, (2) an uploaded (BYOM) model, or (3) a Fortanix-provided model (that is, the Yolov5 prebuilt models).
- Next, the input dataset is selected which is filtered by the input file format of the model selected.
- Finally, the app (algorithm) is selected.
Fortanix has a fair usage policy in this Early Customer Access Program. Hence, Fortanix has limited the resources one can create per account. Therefore, it is expected to observe a resource creation failure message once you have reached the max limit.
To report an issue/bug, visit https://support.fortanix.com/hc/en-us/requests/new.