Adding attention bias input to Multi Head Attention parser

[urpetkov-amd]

Motivation

PR has been created as separate PR desired from this PR: #4637
Adding attention bias as new input for MultiHeadAttention parser in order to support some models.

Technical Details

Added attention bias in parse_multi_head_attention.cpp
Added tests covering bias and attention bias changes

Changelog Category

Add a CHANGELOG.md entry for any option other than Not Applicable

• • Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #4680      +/-   ##
===========================================
+ Coverage    92.27%   92.28%   +0.01%     
===========================================
  Files          578      578              
  Lines        28541    28561      +20     
===========================================
+ Hits         26335    26355      +20     
  Misses        2206     2206              

Files with missing lines	Coverage Δ
src/onnx/parse_multi_head_attention.cpp	98.44% <100.00%> (+0.10%)	⬆️

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[TedThemistokleous]

Everything looks good here. Just add a test for verify something simple just take the gold values from a working test and then bias the kv inputs or generate a verify case for the added bias to ensure we don't get regressions if something changes. Otherwise looks good.

[urpetkov-amd]

@TedThemistokleous Tests have been added.