KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
This library addresses the problem of slow adoption of neural network compression techniques for researchers and practitioners by providing a unified and easy-to-use platform.
This paper introduces KD-Lib, an open-source PyTorch library that provides modular implementations of state-of-the-art algorithms for knowledge distillation, pruning, and quantization. The library aims to facilitate the adoption and commercial usage of these neural network compression techniques.
In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. While there has been steady research in this domain, adoption and commercial usage of the proposed techniques has not quite progressed at the rate. We present KD-Lib, an open-source PyTorch based library, which contains state-of-the-art modular implementations of algorithms from the three families on top of multiple abstraction layers. KD-Lib is model and algorithm-agnostic, with extended support for hyperparameter tuning using Optuna and Tensorboard for logging and monitoring. The library can be found at - https://github.com/SforAiDl/KD_Lib.