# NervanaSystems/ngraph

nGraph has moved to OpenVINO

Repository: https://github.com/NervanaSystems/ngraph
Canonical: https://ross.abutalabs.com/products/nervanasystems-ngraph
Homepage: https://www.ngraph.ai/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: ngraph, tensorflow, mxnet, deep-learning, compiler, performance, onnx, paddlepaddle, neural-network, deep-neural-networks, pytorch, caffe2
Archived: true
Last push: 2020-10-15T21:54:02+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": 3327, "days_push": 2148, "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 1344, forks 218 (observed 2026-08-28T04:04:27.117400+00:00)

## What it is
nGraph is a C++ deep learning graph compiler that accelerates neural network workloads from frameworks like TensorFlow, ONNX, MXNet, and PyTorch across diverse hardware targets. The project has been merged into Intel's OpenVINO toolkit and is no longer maintained here.

## Use cases
- compile deep learning graphs for faster inference
- accelerate tensorflow workloads on intel hardware
- run onnx models with a graph compiler
- optimize neural network subgraphs for performance
- deploy deep learning models to intel npu accelerators

## When to choose
- you need the historical ngraph compiler stack for research or legacy builds
- you want to study graph compiler architecture for deep learning

## When to avoid
- you want active maintenance or new features - use OpenVINO instead
- you need current framework version support
- you need GPU support via PlaidML going forward

## Facets
- artifact type: library
- maturity: abandoned
- function: compiler, machine-learning, deep-learning, llm-training
- domain: deep-learning, machine-learning, compilers, performance
- platform: cpp, python
- tags: neural-network-compiler, graph-compiler, onnx, tensorflow-integration, moved-to-openvino, hardware-acceleration, linux, macos

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.117400+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 2026-08-30T04:42:48.610574+00:00, confidence not recorded.
  - readme: https://github.com/NervanaSystems/ngraph (fetched 2026-08-28T04:04:27.117400+00:00, sha 9681cc9eecdb)
- Data as of 2026-08-30T08:39:29.467469+00:00.