jiazhihao/TASO
The Tensor Algebra SuperOptimizer for Deep Learning
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.
Stars
740
Forks
93
Language
C++
License
Apache-2.0
Category
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.
Higher-rated alternatives
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.