OpenPPL/ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
This tool helps AI engineers optimize neural networks for deployment on resource-constrained hardware like edge devices. It takes a pre-trained neural network model (e.g., in ONNX, PyTorch, or Caffe format) and converts its floating-point calculations to fixed-point, resulting in a smaller, faster model with reduced power consumption. The output is a quantized model ready for deployment on specific hardware platforms, making AI applications more efficient.
1,788 stars. No commits in the last 6 months.
Use this if you need to significantly reduce the computational cost, memory footprint, and power consumption of your neural network models for efficient deployment on edge devices or specialized hardware.
Not ideal if your neural network models are already optimized for your target hardware, or if you do not require a reduction in model size or power usage.
Stars
1,788
Forks
274
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OpenPPL/ppq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...