# tenstorrent/tt-metal

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

Repository: https://github.com/tenstorrent/tt-metal
Canonical: https://ross.abutalabs.com/products/tt-metal
Homepage: https://docs.tenstorrent.com/tt-metal/latest/ttnn/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: llama, llm, metal, stable-diffusion, tenstorrent, accelerator, scale-out, kernels, ai, deepseek, gpu, img-gen, video-gen, cuda
Last push: 2026-08-26T19:58:43+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 92
- inputs: {"age_days": 1297, "days_push": 7, "days_rel": 22, "gap_med": 17.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1640, forks 613 (observed 2026-08-28T04:05:15.276892+00:00)

## What it is
TT-Metal is Tenstorrent's open-source software stack containing TT-NN, a Python and C++ neural network operator library, and TT-Metalium, a low-level kernel programming model and SDK for Tenstorrent AI accelerators. It enables running and optimizing models like Llama, Qwen, and Stable Diffusion directly on Tenstorrent hardware such as Wormhole, Blackhole, and Galaxy systems.

## Use cases
- run LLM inference on Tenstorrent hardware
- write custom kernels for Tensix cores
- port PyTorch models to Tenstorrent accelerators
- serve Llama 3.3 70B with tensor parallelism across devices
- optimize stable diffusion image generation on AI accelerators
- benchmark tokens-per-second throughput on Wormhole Galaxy clusters
- develop fused transformer operations with a PyTorch-like API

## When to choose
- you own Tenstorrent hardware (Grayskull, Wormhole, Blackhole, Galaxy) and want to run or optimize models
- you need low-level, bare-metal access to Tenstorrent silicon for custom kernel development
- you want pre-optimized neural network operations via a PyTorch-familiar Python or C++ API
- you are deploying high-throughput LLM inference with vLLM on Tenstorrent systems

## When to avoid
- you only have NVIDIA/AMD GPUs and no Tenstorrent hardware
- you want a framework-agnostic compiler path without custom kernel work (consider TT-Forge instead)
- you need a turnkey inference server UI (consider tt-inference-server or TT-Studio)
- you require broad OS support beyond Ubuntu 22.04, which is the recommended platform

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, gpu-computing, sdk, compiler
- domain: deep-learning, large-language-models, gpu-computing, hardware, developer-tools
- platform: cpp, python
- tags: tenstorrent, ttnn, tt-metalium, neural-network-operators, custom-kernels, tensix, wormhole, blackhole, tensor-parallelism, hardware-accelerator, linux

## Member repositories
- tenstorrent/tt-metal (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:15.276892+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:46:24.750931+00:00, confidence not recorded.
  - readme: https://github.com/tenstorrent/tt-metal (fetched 2026-08-28T04:05:15.276892+00:00, sha e6c4707fce44)
  - homepage: https://docs.tenstorrent.com/tt-metal/latest/ttnn/ (fetched 2026-08-29T11:19:34.855766+00:00, sha 8c763d308c9d)
  - site_page: https://docs.tenstorrent.com/getting-started/README.html (fetched 2026-08-29T11:19:34.872891+00:00, sha 9788f7e55496)
  - site_page: https://docs.tenstorrent.com/getting-started/manual-software-install.html (fetched 2026-08-29T11:19:34.876109+00:00, sha 733dc7001c7e)
  - site_page: https://docs.tenstorrent.com/getting-started/vLLM-servers.html (fetched 2026-08-29T11:19:34.878134+00:00, sha 389502b29bb1)
  - site_page: https://docs.tenstorrent.com/ (fetched 2026-08-29T11:19:34.867011+00:00, sha 91c33d71f1c0)
  - site_page: https://docs.tenstorrent.com/getting-started/tt-software-stack.html (fetched 2026-08-29T11:19:34.869996+00:00, sha 37647463bedf)
  - site_page: https://docs.tenstorrent.com/tt-metal/latest/ttnn/ttnn/about.html (fetched 2026-08-29T11:19:34.881926+00:00, sha 3da020d50d66)
  - site_page: https://docs.tenstorrent.com/tt-metal/latest/ttnn/ttnn/installing.html (fetched 2026-08-29T11:19:34.883492+00:00, sha eb7ce7c0d1e5)
  - site_page: https://tenstorrent.com/faq (fetched 2026-08-29T11:19:34.880264+00:00, sha 5639cd7c5d1e)
- Data as of 2026-08-30T08:39:29.467469+00:00.