fix: attention_unfused alpha missing norm_factor squaring
ds_attention passes 1/sqrt(sqrt(head_dim)); attention_unfused used it
directly as QK^T scale (head_dim^(-1/4)). The correct softmax scale is
head_dim^(-1/2), requiring alpha = norm_factor * norm_factor. The
fallback binding in the same file (line 378) already does this —
this fix aligns attention_unfused with it.
Signed-off-by: Guokai Ma <guokai.ma@intel.com>
