Refine Unzip V1: Reduce size of cudaMemset

[pesionzhao]

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

Performance optimization

PR changes

Models

Description

v1: Reduce size of cudaMemsetAsync and get shorter execution time

[paddle-bot]

Thanks for your contribution!

[pesionzhao]

/re-run all-failed