llama&qwen2 A8W8 support skip_scale

[ming1753]

PR types

Bug fixes

PR changes

Models

Description

支持llama和qwen2 W8A8 跳层量化

[paddle-bot[bot]]

Thanks for your contribution!

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 0% with 231 lines in your changes missing coverage. Please review.

Project coverage is 53.25%. Comparing base (db270d9) to head (fa56eaf). Report is 278 commits behind head on develop.

Files with missing lines	Patch %	Lines
...erimental/transformers/fused_transformer_layers.py	0.00%	115 Missing :warning:
...dlenlp/experimental/transformers/llama/modeling.py	0.00%	55 Missing :warning:
...dlenlp/experimental/transformers/qwen2/modeling.py	0.00%	54 Missing :warning:
...dlenlp/experimental/transformers/bloom/modeling.py	0.00%	1 Missing :warning:
...enlp/experimental/transformers/chatglm/modeling.py	0.00%	1 Missing :warning:
...p/experimental/transformers/chatglm_v2/modeling.py	0.00%	1 Missing :warning:
...addlenlp/experimental/transformers/gpt/modeling.py	0.00%	1 Missing :warning:
...addlenlp/experimental/transformers/opt/modeling.py	0.00%	1 Missing :warning:
...ddlenlp/experimental/transformers/qwen/modeling.py	0.00%	1 Missing :warning:
...lp/experimental/transformers/qwen2_moe/modeling.py	0.00%	1 Missing :warning:

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #8987      +/-   ##
===========================================
- Coverage    53.29%   53.25%   -0.05%     
===========================================
  Files          652      652              
  Lines       105483   105576      +93     
===========================================
  Hits         56222    56222              
- Misses       49261    49354      +93     

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

[yuanlehome]

Merged with https://github.com/PaddlePaddle/PaddleNLP/pull/9197