modify block_multihead_attention api

[ming1753]

PR types

Others

PR changes

Others

Description

PaddlePaddle/Paddle#64246
Paddledevelop修改了block_multihead_attention，该PR与之对齐。
blha算子新增两个可选参数max_enc_len_this_time和max_dec_len_this_time，在传入时不在kernel内部计算，推理性能提升10%+。

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 5 lines in your changes are missing coverage. Please review.

Project coverage is 54.27%. Comparing base (87e4c4f) to head (7634b64).
Report is 3 commits behind head on develop.

❗ Current head 7634b64 differs from pull request most recent head 11c122e

Please upload reports for the commit 11c122e to get more accurate results.

Files	Patch %	Lines
...erimental/transformers/fused_transformer_layers.py	0.00%	5 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #8456      +/-   ##
===========================================
- Coverage    54.29%   54.27%   -0.03%     
===========================================
  Files          617      617              
  Lines        96339    96361      +22     
===========================================
- Hits         52312    52304       -8     
- Misses       44027    44057      +30     

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

[wawltor]

LGTM