Quantization techniques reduce memory and computational costs by representing weights and activations with lower-precision data types like 8-bit integers (int8). This enables loading larger models you normally wouldn't be able to fit into memory, and speeding up inference.

[[autodoc]] quantizers.PipelineQuantizationConfig

[[autodoc]] quantizers.quantization_config.BitsAndBytesConfig

[[autodoc]] quantizers.quantization_config.GGUFQuantizationConfig

[[autodoc]] quantizers.quantization_config.QuantoConfig

[[autodoc]] quantizers.quantization_config.TorchAoConfig

[[autodoc]] quantizers.base.DiffusersQuantizer