# Torch7

http://torch.ch

Repository: https://github.com/torch/torch7
Canonical: https://ross.abutalabs.com/products/torch7
Language: C
License: NOASSERTION
License Family: other
Last push: 2025-03-31T20:16:24+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 14, release rhythm 35, longevity 100
- inputs: {"age_days": 4702, "days_push": 520, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9141, forks 2338 (observed 2026-08-28T04:10:28.585935+00:00)

## What it is
Torch7 is a scientific computing framework with a fast multi-dimensional tensor library and math operations, originally built for Lua with a C backend (TH, THNN, THC). It was the predecessor to PyTorch and is no longer in active development, with its functionality rewritten in PyTorch's ATen library.

## Use cases
- train neural networks with Lua
- multi-dimensional tensor math operations
- run legacy Torch7 machine learning models
- GPU-accelerated tensor computations with cutorch
- maintain old research codebases built on Torch
- serialize and deserialize arbitrary objects for ML pipelines

## When to choose
- you must run or maintain an existing Torch7/Lua codebase
- you need to reproduce results from older research papers that used Torch

## When to avoid
- starting any new machine learning project
- you want GPU support, sparse tensors, or modern features - use PyTorch instead
- you need community support or recent updates

## Facets
- artifact type: framework
- maturity: abandoned
- function: machine-learning, deep-learning, serialization, math
- domain: machine-learning, deep-learning, developer-tools
- platform: cpp, lua
- tags: tensors, legacy, scientific-computing, lua, gpu-computing, linux, macos

## Member repositories
- torch/torch7 (main) score 39
- torch/nn (plugin) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.585935+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 2026-08-29T17:23:24.535195+00:00, confidence not recorded.
  - readme: https://github.com/torch/torch7 (fetched 2026-08-28T04:10:28.585935+00:00, sha ef820c06d217)
- Data as of 2026-08-30T08:39:29.467469+00:00.