[WIP] Flashattention Support

[futz12]

A Naive and simple impl of Flashattention, Now it can only support dim <= 128 per head section

[codecov-commenter]

Codecov Report

❌ Patch coverage is 93.49112% with 11 lines in your changes missing coverage. Please review.
✅ Project coverage is 92.76%. Comparing base (6b4f6f9) to head (6c5fa84).
⚠️ Report is 5 commits behind head on master.

Files with missing lines	Patch %	Lines
src/layer/vulkan/sdpa_vulkan.cpp	93.49%	11 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #6500      +/-   ##
==========================================
- Coverage   93.27%   92.76%   -0.52%     
==========================================
  Files         845      808      -37     
  Lines      266119   255542   -10577     
==========================================
- Hits       248222   237042   -11180     
- Misses      17897    18500     +603     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

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

[tencent-adm]

Thank you for your submission, we really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ futz12
❌ nihui
_{You have signed the CLA already but the status is still pending? Let us recheck it.}