FromIntXQuantizationAwareTrainingConfig

class torchao.quantization.qat.FromIntXQuantizationAwareTrainingConfig

Object that knows how to convert a model with fake quantized modules, such as FakeQuantizedLinear() and FakeQuantizedEmbedding(), back to model with the original, corresponding modules without fake quantization. This should be used with quantize_().

Example usage:

from torchao.quantization import quantize_
quantize_(
    model_with_fake_quantized_linears,
    FromIntXQuantizationAwareTrainingConfig(),
)