FakeQuantizedLinear

class torchao.quantization.qat.FakeQuantizedLinear(in_features: int, out_features: int, bias: bool = False, activation_config: Optional[FakeQuantizeConfigBase] = None, weight_config: Optional[FakeQuantizeConfigBase] = None, *args, **kwargs)

General linear layer with fake quantized weights and activations.

Specific target dtypes, granularity, schemes etc. are specified through separate configs for weights and activations.

Example usage:

activation_config = IntxFakeQuantizeConfig(
    dtype=torch.int8,
    granularity="per_token",
    is_symmetric=False,
)
weight_config = IntxFakeQuantizeConfig(
    dtype=torch.int4,
    group_size=8,
    is_symmetric=True,
)
fq_linear = FakeQuantizedLinear(
    16, 32, False, activation_config, weight_config,
)
fq_linear(torch.randn(16))

forward(x: Tensor) → Tensor

Runs the forward pass.