ise-uiuc/nnsmith
Automated DNN generation for fuzz testing and more
NNSmith helps developers and quality assurance engineers validate deep learning frameworks and compilers. It automatically generates diverse deep neural network (DNN) models and uses them to fuzz test the framework. This process helps uncover bugs and inconsistencies in how different frameworks (like PyTorch, TensorFlow, or ONNX) handle model definitions and computations.
144 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing or maintaining a deep learning framework or compiler and need a robust way to automatically generate test cases to find bugs and ensure correctness across different backends.
Not ideal if you are an end-user building or deploying deep learning models and not directly involved in the development of the underlying deep learning infrastructure.
Stars
144
Forks
36
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 14, 2025
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ise-uiuc/nnsmith"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...
mlcommons/inference
Reference implementations of MLPerf® inference benchmarks
mlcommons/training
Reference implementations of MLPerf® training benchmarks
datamade/usaddress
:us: a python library for parsing unstructured United States address strings into address components
GRAAL-Research/deepparse
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning