[RL] Add reshard controller

[fjjF77]

PR types

Bug fixes

PR changes

APIs

Description

添加reshard controller控制训练推理时分片设置切换。

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 114 lines in your changes missing coverage. Please review.

Project coverage is 46.94%. Comparing base (ddcb722) to head (a7f938f).
Report is 1 commits behind head on develop.

Files with missing lines	Patch %	Lines
paddlenlp/rl/utils/reshard_utils.py	0.00%	57 Missing ⚠️
paddlenlp/rl/utils/infer_utils.py	0.00%	27 Missing ⚠️
paddlenlp/rl/trainer/rl_trainer.py	0.00%	11 Missing ⚠️
paddlenlp/rl/utils/comm_utils.py	0.00%	11 Missing ⚠️
paddlenlp/rl/trainer/ppo_trainer.py	0.00%	8 Missing ⚠️

❌ Your patch status has failed because the patch coverage (0.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage.
❌ Your project status has failed because the head coverage (46.94%) is below the target coverage (58.00%). You can increase the head coverage or adjust the target coverage.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop   #10606      +/-   ##
===========================================
- Coverage    46.94%   46.94%   -0.01%     
===========================================
  Files          799      799              
  Lines       132348   132364      +16     
===========================================
- Hits         62137    62136       -1     
- Misses       70211    70228      +17     

☔ 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.