Introduction to Quantization on PyTorch
WHAT IS QUANTIZATION?
THE THREE MODES OF QUANTIZATION SUPPORTED IN PYTORCH STARTING VERSION 1.3
Dynamic Quantization
Post-Training Static Quantization
Quantization Aware Training
Device and Operator Support
Choosing an approach
Performance Results
Accuracy results
Conclusion
Further reading

链接:https://pytorch.org/blog/introduction-to-quantization-on-pytorch/