Tensorizer Benchmarks and Examples

Test CoreWeave Tensorizer with our in-depth walkthroughs

CoreWeave's Tensorizer is a module, model, and tensor serializer and deserializer that makes it possible to load models in less than five seconds, making it easier, more flexible, and more cost-efficient to serve models at scale.

Tensorizer benchmark tutorial directory

Each guide includes a link to the source code for the provided example. In most cases, it will be required to clone the repository in order to follow along directly with the tutorial's walkthrough.

Benchmark tutorials

In this tutorial, two inference services are created - one which uses Tensorizer, and one which does not. This benchmark provides comparative metrics on average response time and autoscaling capabilities.

Last updated