TensorFlow Serving for production model inference, enforced behind nginx basic auth with per instance credentials on first boot.
Choose the operating system, cloud and version you need. Every variation is the same hardened TensorFlow Serving image, built and supported by cloudimg.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| TensorFlow Serving With Nginx Auth | AWS | — | Standard | View · Guide |
| TensorFlow Serving 2 Ubuntu 24.04 | Azure | Ubuntu 24.04 | 2 | View · Guide |
TensorFlow Serving is a high performance serving system for machine learning models, exposing trained SavedModels through REST and gRPC inference APIs. It is designed to serve model predictions in production and to manage model versions over time.
The cloudimg image is hardened and fully patched with TensorFlow Serving running under Docker Compose and systemd, a sample model preloaded and nginx basic auth enforced on every request. Per instance credentials are generated on first boot and stored in a root only file so no endpoint is exposed without authentication, and 24/7 cloudimg support is included.