ttnn

Official

TTNN: Fast tensor ops on Tenstorrent hardware.

Authortenstorrent
Version1.0.0
Installs0

System Documentation

What problem does it solve?

TTNN provides high-performance tensor primitives and device management on Tenstorrent hardware, enabling efficient ML workloads and model conversions.

Core Features & Use Cases

  • High-level TTNN APIs for tensor creation, manipulation, and movement across MeshDevice topologies.
  • Multi-device execution across MeshDevice topologies with memory configurations.
  • Model conversion utilities from PyTorch to TTNN compatible formats for accelerated inference.
  • Integration with TT-Metal stack for MLIR pipelines and TT kernels.

Quick Start

Initialize TTNN on a device, convert a PyTorch tensor to TTNN, and execute a simple tensor operation on a MeshDevice.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ttnn
Download link: https://github.com/tenstorrent/tt-forge/archive/main.zip#ttnn

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.