def linear()

in inference/model.py [0:0]

• 12 lines of code
• 4 McCabe index (conditional complexity)

def linear(x: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None) -> torch.Tensor:
    """
    Applies a linear transformation to the incoming data: y = xA^T + b.
    This function supports specialized implementations based on quantization
    and tensor formats.

    Args:
        x (torch.Tensor): The input tensor.
        weight (torch.Tensor): The weight tensor. It may be quantized and 
            requires dequantization for certain cases.
        bias (Optional[torch.Tensor]): The bias tensor to be added. Default is None.

    Returns:
        torch.Tensor: The result of the linear transformation, which may involve 
        quantization-aware computations depending on the input parameters.

    Notes:
        - If `weight` is quantized (e.g., `element_size() == 1`), a dequantized version 
          is used for computation.
        - If `gemm_impl == "bf16"`, dequantization and a `bf16` GEMM operation are applied.
        - For other cases, the function applies quantization to `x` and uses `fp8_gemm` for computation.
    """
    if weight.element_size() > 1:
        return F.linear(x, weight, bias)
    elif gemm_impl == "bf16":
        weight = weight_dequant(weight, weight.scale)
        return F.linear(x, weight, bias)
    else:
        x, scale = act_quant(x, block_size)
        y = fp8_gemm(x, scale, weight, weight.scale)
        if bias is not None:
            y += bias
        return y