jiazhihao/TASO

The Tensor Algebra SuperOptimizer for Deep Learning

46
/ 100
Emerging

This tool helps deep learning engineers and researchers make their neural network models run faster without changing the model's accuracy. You input an existing deep neural network model (like a pre-trained ONNX, TensorFlow, or PyTorch model), and it outputs an optimized version of that model. This is for anyone who deploys deep learning models and needs to improve their inference performance.

740 stars. No commits in the last 6 months.

Use this if you need to accelerate the inference speed of your deep neural networks, especially for deployment on GPUs.

Not ideal if you are looking for a tool to train models or if your primary concern is model accuracy rather than execution speed.

deep-learning-deployment neural-network-optimization model-inference GPU-acceleration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

740

Forks

93

Language

C++

License

Apache-2.0

Last pushed

Jan 26, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jiazhihao/TASO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.