# sony/nnabla

Neural Network Libraries

Repository: https://github.com/sony/nnabla
Canonical: https://ross.abutalabs.com/products/nnabla
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2026-07-24T10:07:47+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 3356, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2774, forks 335 (observed 2026-08-28T04:07:19.123024+00:00)

## What it is
Sony's Neural Network Libraries (nnabla) is a deep learning framework with a Python API over a C++11 core, designed for research, development, and production across desktops, HPC clusters, embedded devices, and servers. The project officially reached end of life on April 3, 2025, with no further development or security support.

## Use cases
- train neural networks in python
- deep learning framework for research and production
- run inference on embedded devices
- gpu-accelerated neural network training with cuda
- deploy neural networks to hpc clusters

## When to choose
- you need a lightweight deep learning framework with a C++ core and embedded/C runtime deployment
- you are maintaining an existing nnabla-based codebase

## When to avoid
- starting a new project - the project is end-of-life with no security support
- you need an actively maintained framework with current CUDA support
- you need the latest model architectures or ecosystem tooling

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, llm-training
- domain: deep-learning, machine-learning, artificial-intelligence
- platform: python, windows, cpp
- tags: neural-networks, cuda-extension, embedded-deployment, end-of-life, linux, macos, gpu, docker

## Member repositories
- sony/nnabla (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:19.123024+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 2026-08-30T08:16:35.693246+00:00, confidence not recorded.
  - readme: https://github.com/sony/nnabla (fetched 2026-08-28T04:07:19.123024+00:00, sha 9cadca2fcb6c)
  - registry_pypi: https://pypi.org/pypi/nnabla/json (fetched 2026-08-29T09:55:58.081765+00:00, sha 384537e4ba5d)
- Data as of 2026-08-30T08:39:29.467469+00:00.