submission 66250

import torch

def custom_kernel(data):
    """
    Highly optimized grayscale conversion of RGB to Y using PyTorch.
    Args:
        data: tuple of (x, y)
            x: input RGB tensor, shape (H, W, 3), values in [0,1]
            y: output grayscale tensor, shape (H, W), values in [0,1]

    Returns:
        y with grayscale values written in-place.
    """
    x, y = data
    
    # Standard luminance coefficients, placed on correct device & dtype
    weights = torch.tensor([0.2989, 0.5870, 0.1140], device=x.device, dtype=x.dtype)

    # Optimized dot product along the last dimension with no intermediate tensor creation
    y.copy_(torch.tensordot(x, weights, dims=([-1], [0])))
    
    return y