# microsoft/nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

Repository: https://github.com/microsoft/nnfusion
Canonical: https://ross.abutalabs.com/products/nnfusion
Language: C++
License: MIT
License Family: permissive
Last push: 2024-09-19T06:31:57+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2345, "days_push": 713, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1002, forks 166 (observed 2026-09-03T02:15:15.037078+00:00)

## What it is
NNFusion is a flexible and efficient deep neural network (DNN) compiler that generates high-performance executables from model descriptions such as TensorFlow frozen models and ONNX files. It performs full-stack optimizations including kernel fusion, memory layout optimization, and ahead-of-time code generation with minimal runtime dependencies.

## Use cases
- compile a frozen TensorFlow or ONNX model into a fast standalone executable
- deploy a pre-trained DNN model without framework dependencies
- speed up inference of a pre-defined deep learning model on CUDA or ROCm GPUs
- experiment with custom compiler optimizations for specific neural network models
- generate human-readable source code from a model to hand-tune kernels
- run distributed parallel training with SuperScaler integration

## When to choose
- you need framework-free, low-overhead deployment of TensorFlow or ONNX models on GPUs
- you want ahead-of-time compilation instead of runtime graph execution
- you are a researcher prototyping compiler optimizations for DNNs
- you need kernel fusion and memory layout tuning for inference performance

## When to avoid
- you need broad model format support beyond TensorFlow and ONNX
- you primarily target Windows or macOS, since support is focused on Ubuntu with CUDA
- you want an actively evolving project, as development appears to be in maintenance mode
- you need dynamic-shape or training-focused compilation without extra tooling

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: compiler, machine-learning, deep-learning, llm-inference, gpu-computing, developer-tools
- domain: machine-learning, deep-learning, compilers, gpu-computing, developer-tools
- platform: cpp
- tags: dnn-compiler, code-generation, onnx, tensorflow, kernel-fusion, ahead-of-time-compilation, inference, linux, docker, gpu

## Member repositories
- microsoft/nnfusion (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.037078+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 2026-08-30T07:14:01.194765+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/nnfusion (fetched 2026-09-03T02:15:15.037078+00:00, sha 6df70f16ef67)
- Data as of 2026-08-30T08:39:29.467469+00:00.