【Inference】Support mtp serving

[freeliuzc]

Before submitting

• Lint code. If there are lint issues, please format the code first.

# Install and register `pre-commit` in the project folder
pip install pre-commit && pre-commit install

# Process previous code files separately
pre-commit run --file XXXX.py

• Add test cases into tests folder. If there are codecov issues, please add tests cases first.

PR types

New features

PR changes

APIs

Description

1. support DeepSeekV3 with MTP in serving mode
2. Unify proposer in predictor and serving

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 160 lines in your changes missing coverage. Please review.

Project coverage is 51.29%. Comparing base (30df8b6) to head (5a26682).
Report is 343 commits behind head on develop.

Files with missing lines	Patch %	Lines
paddlenlp/experimental/transformers/proposers.py	0.00%	157 Missing ⚠️
paddlenlp/transformers/model_utils.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #9936      +/-   ##
===========================================
- Coverage    51.34%   51.29%   -0.05%     
===========================================
  Files          745      745              
  Lines       118590   118690     +100     
===========================================
  Hits         60886    60886              
- Misses       57704    57804     +100     

☔ 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.