Quickstart

This chapter quickly runs through an entire a workflow for using Deci to accelerate your models’ performance.

The following describes how to upload your model to Deci, optimize it for a variety of target production hardware environments, benchmark it, deploy it and then use it for inference in a production environment.

Updated over 1 year ago

What’s Next

Step 1 – Launching the Deci Platform
Step 2 – Exploring an Example Project
Step 3 – Adding Your Model
Step 4 – Optimizing Your Model
Step 5 – Benchmarking Your Model(s)
Step 6 – Deploying and Launching the Inference Engine (RTiC)
Step 7 – Measuring Your Model’s Performance during Production
Step 8 – Serving Your Model – Production Inference

Did this page help you?