Overview

This section describes the AMCT-based quantization scenarios and the 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 quantized model fails to meet the accuracy requirements, perform automatic quantization (recommended) or manual tuning.