tenstorrent/tt-metal

:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.

73
/ 100
Verified

This project offers a Python and C++ library for deploying and running large language models (LLMs) and other neural networks on Tenstorrent AI hardware. It takes trained models and efficiently runs them, providing metrics like tokens per second and first token generation time. AI infrastructure engineers and machine learning practitioners who need to deploy and optimize neural network inference on Tenstorrent hardware would use this.

1,379 stars. Actively maintained with 1,025 commits in the last 30 days.

Use this if you are a machine learning engineer or researcher focused on deploying and optimizing the performance of large AI models, especially LLMs and Whisper, on Tenstorrent's AI accelerators.

Not ideal if you are looking for a general-purpose machine learning framework or if your primary interest is in training models on other hardware platforms.

AI inference large language models neural network deployment AI hardware optimization machine learning engineering
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,379

Forks

375

Language

C++

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

1025

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tenstorrent/tt-metal"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.