Skip to main content

Tenstorrent AI Accelerator

Vendor: Tenstorrent

Category: ASIC Dedicated Accelerator

Architecture: Tensix / RISC-V

Introduction

Tenstorrent's AI accelerators (Wormhole/Grayskull/Blackhole) use a unique Tensix architecture combining RISC-V cores with AI tensor compute units. Led by legendary chip architect Jim Keller, with an open-source software stack.

Specifications

ModelComputeMemoryInterfaceTDPProcess
Wormhole n300200 TFLOPS (BF16)64GB LPDDR5PCIe 5.0 + Ethernet200W6nm
Grayskull e15050 TFLOPS (BF16)16GB GDDR6PCIe 4.075W12nm

Official Website

Visit Official Website

Driver Downloads

Linux

OS Support

WindowsLinuxmacOSAndroid

Version History

VersionRelease DateDescription
TT-Metalium 1.02024RISC-V open-source software stack

Performance Benchmarks

ModelTaskPerformance Metric
Wormhole n300LLM InferenceMedium-scale inference optimized
Grayskull e150Edge AIEntry-level

Pricing

ModelReference PriceNotes
Wormhole n300~$699-999Developer card
Grayskull e150~$399-599Entry-level developer card

Quick Installation

Linux (Ubuntu 22.04)

# 1. Install Tenstorrent driver
pip install tt-torch

# 2. Verify
tt-smi

Obtain drivers and tools from Tenstorrent GitHub.

Code Examples

Python (PyTorch TT)

import torch
import tt_lib

# Use Tenstorrent backend
device = tt_lib.device.CreateDevice()
tt_lib.device.SetDefaultDevice(device)

# tt-torch provides PyTorch backend
x = torch.randn(1024, 1024)
# Automatically routes to Tenstorrent hardware

Architecture Highlights

  • Tensix Core: Programmable tensor cores based on RISC-V, each containing a matrix engine and routing engine
  • Wormhole Interconnect: High-bandwidth inter-chip/card interconnect supporting mesh topology
  • Open-Source Path: Open hardware design and software stack with an active developer community

Model Compatibility

Model/FrameworkSupportNotes
PyTorch✅ tt-torchBackend under development
Cerebras NNSimilar dataflow architecture
LLM Inference⚠️Community adaptation in progress
General AI⚠️Early ecosystem stage

If you're evaluating alternatives, the following products may also fit your scenario: