[LLM INFER] Optimize fuse some kernels in postprocess

[gzy19990617]

PR types

Performance optimization

PR changes

Others

Description

1.get_padding_offset与remove_padding kernel fuse
2.stop_generation_multi_ends_v2与update_inputs kernel与前面的一些操作进行fuse
3.set_value_by_flags_and_idx_v2与set_stop_value_multi_ends_v2 kernel fuse

均增加测试代码，算子级别已对齐精度

[codecov]

Codecov Report

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

Project coverage is 53.19%. Comparing base (8b2cc08) to head (7ed0de5).
Report is 10 commits behind head on develop.

Files with missing lines	Patch %	Lines
...enlp/experimental/transformers/generation_utils.py	0.00%	5 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #9201      +/-   ##
===========================================
+ Coverage    53.16%   53.19%   +0.02%     
===========================================
  Files          657      657              
  Lines       106311   106699     +388     
===========================================
+ Hits         56524    56762     +238     
- Misses       49787    49937     +150     

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