# NervanaSystems/neon

Intel® Nervana™ reference deep learning framework committed to best performance on all hardware

Repository: https://github.com/NervanaSystems/neon
Canonical: https://ross.abutalabs.com/products/nervanasystems-neon
Homepage: http://neon.nervanasys.com/docs/latest
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, python, neon, mkl, performance, fast, neural-network
Archived: true
Last push: 2020-12-23T01:21:42+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4340, "days_push": 2080, "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 3861, forks 804 (observed 2026-08-28T04:08:27.539207+00:00)

## What it is
neon was Intel Nervana's reference deep learning framework in Python, focused on best-in-class training performance on CPUs, GPUs, and Nervana hardware. Intel has officially discontinued the project and no longer accepts patches or provides support.

## Use cases
- train convolutional neural networks fast on GPUs
- train deep learning models on CPUs with MKL acceleration
- build RNN, LSTM, and GRU models
- use pre-trained models from a model zoo
- write model code once and run on swappable hardware backends

## When to choose
- studying the internals of a high-performance deep learning framework
- maintaining a legacy codebase already built on neon
- forking to independently develop a high-performance CPU/GPU training backend

## When to avoid
- starting any new deep learning project
- needing bug fixes, updates, or community support
- wanting modern features like transformers or ecosystem integrations

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning, gpu-computing
- platform: python
- tags: neural-networks, mkl, discontinued, performance, linux, macos, gpu

## Member repositories
- NervanaSystems/neon (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.539207+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 2026-08-29T18:25:53.636008+00:00, confidence not recorded.
  - readme: https://github.com/NervanaSystems/neon (fetched 2026-08-28T04:08:27.539207+00:00, sha 0aaf8e3e566d)
- Data as of 2026-08-30T08:39:29.467469+00:00.