Get Started
Tutorials
Notebooks
Projects
Experiments
Jobs
Models
Deployments
Machines
Data
Gradient SDK
Gradient Private Cloud
Instances
Release Notes

Optimizing Models for Inference

Gradient supports deployment of models compatible with industry standards such as Tensorflow. There are a variety of optimizations you can perform on Tensorflow neural network graphs to reduce their size and latency for inference. Because we use TF Serving for TensorFlow models, we are able to support deployment of these optimized graphs.