def weight_dequant()

in inference/kernel.py [0:0]

• 8 lines of code
• 3 McCabe index (conditional complexity)

def weight_dequant(x: torch.Tensor, s: torch.Tensor, block_size: int = 128) -> torch.Tensor:
    """
    Dequantizes the given weight tensor using the provided scale tensor.

    Args:
        x (torch.Tensor): The quantized weight tensor of shape (M, N).
        s (torch.Tensor): The scale tensor of shape (M//block_size, N//block_size).
        block_size (int, optional): The block size to use for dequantization. Defaults to 128.

    Returns:
        torch.Tensor: The dequantized weight tensor of the same shape as `x`.

    Raises:
        AssertionError: If `x` or `s` are not contiguous or if their dimensions are not 2.
    """
    assert x.is_contiguous() and s.is_contiguous(), 'Input tensors must be contiguous'
    assert x.dim() == 2 and s.dim() == 2, 'Input tensors must have 2 dimensions'
    M, N = x.size()
    y = torch.empty_like(x, dtype=torch.get_default_dtype())
    grid = lambda meta: (triton.cdiv(M, meta['BLOCK_SIZE']), triton.cdiv(N, meta['BLOCK_SIZE']))
    weight_dequant_kernel[grid](x, s, y, M, N, BLOCK_SIZE=block_size)
    return y