Expand description
Quantization module Quantization support for neural networks
This module provides comprehensive quantization capabilities including:
- Post-training quantization (PTQ)
- Quantization-aware training (QAT)
- Mixed bit-width operations
- Dynamic and static quantization schemes
Modules§
- utils
- Quantization utilities and helper functions
Structs§
- Dynamic
Quantizer - Dynamic quantization at runtime
- Mixed
BitWidth Quantizer - Mixed bit-width quantization support
- Post
Training Quantizer - Post-training quantization (PTQ) implementation
- Quantization
Aware Training - Quantization-aware training (QAT) support
- Quantization
Config - Quantization configuration
- Quantization
Params - Quantization parameters for a tensor
- Quantized
Tensor - Quantized tensor representation
Enums§
- Quantization
Mode - Quantization mode
- Quantization
Scheme - Quantization scheme