Checkpoints and Datasets are now supported output destinations for proxiML Training and Inference jobs.

Checkpoints can now be created directly from public or private Hugging Face models.

Get started building models even faster by using Public Checkpoints.

proxiML now supports the creation and use of Checkpoints to store immutable versions of large model weight files.

Google Drive files can now be downloaded directly into proxiML Datasets and Models.

Analytics providers can now run their models directly on the proxiML deployments of their customers. This allows the analytics provider to maintain and protect their intellectual property while providing analytics services inside their customers' secure, private infrastructure.

Run real-time inference workloads on NVIDIA Jetson fully managed by CloudBender™.

Physical CloudBender™ regions now support running a centralized storage controller similar to cloud regions.

Integration with Azure Blob Storage and Azure Container Registry is now available natively in proxiML.

CloudBender™ now allows you deploy applications as endpoints to your local region, so they are only accessible from inside your infrastructure.