Add benchmark for tensor_fusion and overlap in llama7b N4C32 dy_auto

[Xing-lil]

…32_Stage2.sh

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

Others

PR changes

Others

Description

Add benchmark for tensor_fusion and overlap in llama7b N4C32 dy_auto

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 46.95%. Comparing base (ddcb722) to head (9fd8242).
Report is 23 commits behind head on develop.

❌ Your project status has failed because the head coverage (46.95%) 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   #10599   +/-   ##
========================================
  Coverage    46.94%   46.95%           
========================================
  Files          799      799           
  Lines       132348   132348           
========================================
+ Hits         62137    62139    +2     
+ Misses       70211    70209    -2     

☔ 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.

[lugimzzz]

LGTM

[liym27]

LGTM