Add Pipeline Parallel for PPO training and support generation with InferenceModel

[guoshengCS]

PR types

New features

PR changes

Others

Description

Add Pipeline Parallel for PPO training and support generation with InferenceModel

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 30.55556% with 25 lines in your changes missing coverage. Please review.

Project coverage is 54.41%. Comparing base (b36b6a0) to head (f1e66f2). Report is 53 commits behind head on develop.

Files	Patch %	Lines
paddlenlp/utils/nested.py	11.11%	16 Missing :warning:
paddlenlp/transformers/llama/modeling_pp.py	28.57%	5 Missing :warning:
paddlenlp/generation/utils.py	33.33%	2 Missing :warning:
paddlenlp/trainer/plugins/timer.py	0.00%	1 Missing :warning:
paddlenlp/transformers/model_utils.py	0.00%	1 Missing :warning:

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #7953      +/-   ##
===========================================
+ Coverage    54.29%   54.41%   +0.12%     
===========================================
  Files          617      632      +15     
  Lines        96339    99476    +3137     
===========================================
+ Hits         52310    54134    +1824     
- Misses       44029    45342    +1313     

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[CLAassistant]

All committers have signed the CLA.