[LLM] support sparse attention for LLAMA

[GuoxiaWang]

PR types

New features

PR changes

Models

Description

[LLM] support sparse attention for LLAMA

[paddle-bot[bot]]

Thanks for your contribution!

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 14.89362% with 40 lines in your changes missing coverage. Please review.

Project coverage is 54.17%. Comparing base (a8d446c) to head (61f2314). Report is 1 commits behind head on develop.

Files	Patch %	Lines
paddlenlp/transformers/llama/modeling_pp.py	10.25%	35 Missing :warning:
paddlenlp/transformers/llama/fusion_ops.py	0.00%	4 Missing :warning:
paddlenlp/transformers/llama/modeling.py	75.00%	1 Missing :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## develop #8592 +/- ## =========================================== - Coverage 54.18% 54.17% -0.02% =========================================== Files 625 625 Lines 98942 98972 +30 =========================================== + Hits 53612 53615 +3 - Misses 45330 45357 +27 ```

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