Developers

Learn how to get your models up and running fast on Tenstorrent hardware. With two open source SDKs, you can get as close to the metal as possible, or let our AI compiler do the work.
Developers

Getting started on Tenstorrent

Looking for other documentation?
Upcoming Events
Apr 29
Generative AI Summit

Join us in Santa Clara for the Generative AI Summit. Learn more about how you can get started on Tenstorrent hardware, and try out our developer cloud.

Apr 30
Compilers: Modeling Multi-Device and Scale-Out

As machine learning models grow in complexity, executing them efficiently across multiple devices is crucial for scalability and performance. In this talk, Tenstorrent engineer Tapasvi Patel will explore compiler-based techniques for modeling multi-device execution and scale-out strategies.

May 10
Legacy Code Meets Tensor Compute

Daisytuner is hosting a Tenstorrent hackathon at the Daisytuner HQ in Darmstadt, Germany. In this hackathon, participants will take on the challenge of compiling legacy code to run efficiently on Tenstorrent Wormhole.

Educational Content

Tutorials

Intro to TT-Forge
Tutorials
Intro to TT-Forge
An overview of TT-Forge, Tenstorrent's MLIR-based compiler.
TT-Metalium Programming Overview
Tutorials
TT-Metalium Programming Overview
A guide to the Metalium programming model, Tenstorrent’s primary programming model.
How to Use the TTNN Visualizer
Tutorials
How to Use the TTNN Visualizer
Learn how to install and run ttnn-visualizer. ttnn-visualizer helps you gain a complete understanding of a model.

Written Tutorials

Bring up LLMs with TTNN
Get guidance on how to bring up high-performance multi-chip models on Tenstorrent hardware using the TT-Metalium stack.
Get started with TTNN-Visualizer
A quickstart guide to setting up ttnn-visualizer.
Build a graph of a PyTorch based model
In this tutorial, we walk you through the steps of building a graph of a pytorch model.

Join the Community

Get access to support on anything from setting up new hardware, running models or optimizing your setup, plus the latest on Tenstorrent hardware and software.
Community

Interested in contributing?

Tenstorrent's AI software stack is open source. Getting started is as easy as filing an issue.