fused_fftconv2d_supported

fused_fftconv2d_supported(x_dim, y_dim, k_x, k_y)

Whether the fused 2D kernel can handle this input/kernel shape combination.

A cheap, exception-free probe over the same rules as resolve_fused_fft_size() — useful for backend auto-selection and for the torch.compile pattern-match guard.

Parameters:

• x_dim (int) – Input height X.

• y_dim (int) – Input width Y.

• k_x (int) – Kernel height K_x.

• k_y (int) – Kernel width K_y.

Returns:

True if an admissible FFT tile exists, False otherwise.

Return type:

bool