【Inference】optimize preprocess

[gzy19990617]

PR types

Performance optimization

PR changes

Others

Description

1.get_padding_offset与remove_padding kernel合并
2.stop_generation_multi_ends_v2与update_inputs kernel合并

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

root seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 17 lines in your changes missing coverage. Please review.

Project coverage is 53.06%. Comparing base (9806293) to head (5ecd24f).
Report is 33 commits behind head on develop.

Files with missing lines	Patch %	Lines
...enlp/experimental/transformers/generation_utils.py	0.00%	17 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #9175      +/-   ##
===========================================
- Coverage    53.34%   53.06%   -0.29%     
===========================================
  Files          652      656       +4     
  Lines       105401   106151     +750     
===========================================
+ Hits         56222    56324     +102     
- Misses       49179    49827     +648     

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