[LLM] Add fused attention in Qwen2MoE

[DrownFish19]

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

Models

Description

add fuse_attention_qkv and fuse_attention_ffn to Qwen2MoE.

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

Attention: Patch coverage is 48.78049% with 63 lines in your changes missing coverage. Please review.

Project coverage is 52.36%. Comparing base (fb60645) to head (9acff15).
Report is 8 commits behind head on develop.

Files with missing lines	Patch %	Lines
paddlenlp/transformers/qwen2_moe/modeling.py	48.78%	63 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #9767      +/-   ##
===========================================
- Coverage    52.70%   52.36%   -0.34%     
===========================================
  Files          731      727       -4     
  Lines       117313   115245    -2068     
===========================================
- Hits         61827    60352    -1475     
+ Misses       55486    54893     -593     

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