Skip to content

What is Tenstorrent?

Tenstorrent is a team of competent and motivated people that came together to build the best computing platform for AI and Software 2.0.

Can I use your AI hardware for training or inference?

Yes, our computers are optimized for neural network inference and training. They can also execute other types of parallel computation.

What is Tenstorrent doing differently than GPUs?

Tenstorrent computers are made of arrays of processors known as Tensix cores. Our processors are capable of executing small and large tensor computations efficiently. Network communication hardware is present in each processor, and they talk with one another directly over networks, instead of through DRAM. Our computers are easier to program, scale better, and are excellent at handling run-time sparsity and conditional computation.

What ML frameworks are supported by your hardware?

We have focused our efforts on Pytorch for now, but are capable of interfacing to other frameworks via ONNX. We also have a low level c++ based programming framework called Buda, and are able to run computations on numpy arrays.

What is a 'Tensix' core?

Tenstorrent's processor is known as Tensix. Each Tensix includes 5 RISC processors, an array math unit for tensor operations, a SIMD unit for vector operations, hardware for accelerating network packet operations and compression/decompression, and 1-2 megabytes of SRAM.

Is my system compatible with a Tenstorrent Grayskull card?

You’ll need a Linux system running Ubuntu or Centos, with one or more free PCIe x16 slots, and a system power supply that is able to provide adequate power.

What is the installation process and what support do I get?

Install the card into your system, download our driver and install it by running an install script as root, and download and run our docker file. Installation usually takes 30 minutes to an hour. If you have trouble with the process, and we'll talk you through it.

Where can I buy a Tenstorrent card or system?

You can buy Grayskull products or through one of our distribution partners.

I host and train my ML applications through a Cloud Service Provider. What options do I have?

For starters, you can try using our computers through Tenstorrent DevCloud. We are also partnering with cloud providers to enable customers like yourself to use our computers in the cloud commercially. For more information, click here.

I'd like to evaluate a Tenstorrent chip for my application, how do I do that?

with us to discuss your needs.

How can I become a Tenstorrent distributor/reseller?

We are interested in expanding our distribution network. Please with us to discuss.

Contact Us

    By submitting this form, you agree to receive email communication from Tenstorrent. You can opt out at any time.