[WebNN EP] Support local attention feature for GQA

[peishenyan]

Description

Support the local_window_size attribute in GroupQueryAttention Operator, which is designed for sliding window attention and may influence the attention mask pattern.

For local window size not equal to -1, new attention mask pattern will be created as follows for applying sliding window.

     condition_1 (old attn_mask) ---> CumSum (axis=3, exclusive=true, reversed=true)
          |                             |
          |                           Lesser <--- local_window_size
          |                             |
      LogicalAnd <----------------- condition_2
          |
    new attn_mask

Motivation and Context

[peishenyan]

PTAL, thanks. @Honry

[Honry]

Thanks, LGTM, pls. also mention the needs to use 'expand' for mask_shape_ones_shape_constant in your commit message.

[Honry]

• @fdwr, please take another look, thanks!