Skip to content

Excited about the future of AI hardware? Apply to be a part of the Tenstorrent team >

Tenstorrent Software

Tenstorrent has two distinct
software approaches:

TT-Buda™: Run any model right away

Great for production customers who want to get models up and running with ease. They want flexibility, but don’t have time to program new operations or contact support every time something changes.

TT-Metalium: Open Access to Tenstorrent Hardware & Software

Great for development customers who want to customize their models, write new ones or even run non-machine learning code. No black boxes, encrypted APIs, or hidden functions.

TT-Metalium is a low-level software platform for a heterogeneous collection of CPUs and Tenstorrent devices, giving users direct access to the RISC-V processors, NoC (Network-on-Chip), and Matrix and Vector engines within the Tensix Core.

20231030_Native_Scale_Out_ks-05 1
Native Tensor Compute
20231030_Native_Scale_Out_ks-06 1
Native Tensor Compute
20231030_Native_Scale_Out_ks-07 1
20231030_Native_Scale_Out_ks-08 1
Native Multi Chip Scale Out

The figure below shows the software layers that can be built on top of the TT-Metalium platform. With TT-Metalium, developers can write host and kernel programs that can implement a specific math operation (e.g., matrix multiplication, image resizing etc.), which are then packaged into libraries. Using the libraries as building blocks, various frameworks provide the user with a flexible high-level environment in which they can develop a variety of HPC and ML applications.

No Customization Required
  • Python APIs
  • Easy to Use
  • Intuitive, PyTorch-like
Lightweight Optimization/Perf
  • Batch
  • Library of 
Fused OPs
  • Op Selection & Parallelization
  • Data formats & Math Fidelity
  • Tensor Storage L1 or DRAM
  • Augmented Python APIs
Heavyweight Optimization

Write your own custom kernels & OPs

  • Fused Kernels
  • TMs

Go into Metalium Code

  • Write C++ kernels
  • Understand the Hardware
  • Low-level Optimization