restructure the multi-head attention layer

[jijoongmoon]

We can optimize the memory consumption of the multi-head attention layer by combination of layers. By doing this, we could reduce the memory further.

1. compute multi-head one by one.
2. re-implement the multi-head attention layer as an backbone layer.

[taos-ci]

:octocat: cibot: Thank you for posting issue #1998. The person in charge will reply soon.

[lhs8928]

To list for 1

• [ ] Enhance split layer to split input by given number(number of head). #2025
• [ ] Replace a multi head attention layer by make a sub-graph
• [ ] Compare the peak memory consumption and latency before and after changes
• [ ] Compare the peak memory consumption and latency before and after enabling the swap feature