Overview
This section describes the quantization scenarios supported by AMCT and functions in each scenario.
Quantization takes two forms: Manual Quantization and Automatic Quantization based on whether the quantization configuration file is manually tuned after quantization. For details about the quantization algorithms for PTQ, see Compression Concepts. For details about the quantization concepts, see Compression Concepts.
If the accuracy of the quantized model is not as expected, perform Automatic Quantization (recommended) or Manual Tuning until the accuracy meets your requirement.
Parent topic: Quantization