xpu devices support llama-7b basic mode inference (turn on BlockAtten…

[zhink]

…tion)

PR types

New features

PR changes

Others

Description

xpu devices support llama-7b basic mode inference (turn on BlockAttention)

[paddle-bot]

Thanks for your contribution!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 31 lines in your changes missing coverage. Please review.

Project coverage is 54.41%. Comparing base (525eef7) to head (8717c5e).
Report is 239 commits behind head on develop.

Files with missing lines	Patch %	Lines
...erimental/transformers/fused_transformer_layers.py	0.00%	11 Missing ⚠️
...enlp/experimental/transformers/generation_utils.py	0.00%	9 Missing ⚠️
...dlenlp/experimental/transformers/llama/modeling.py	0.00%	3 Missing ⚠️
...dlenlp/experimental/transformers/bloom/modeling.py	0.00%	2 Missing ⚠️
...ddlenlp/experimental/transformers/qwen/modeling.py	0.00%	2 Missing ⚠️
...enlp/experimental/transformers/chatglm/modeling.py	0.00%	1 Missing ⚠️
...p/experimental/transformers/chatglm_v2/modeling.py	0.00%	1 Missing ⚠️
...addlenlp/experimental/transformers/gpt/modeling.py	0.00%	1 Missing ⚠️
...addlenlp/experimental/transformers/opt/modeling.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #8588      +/-   ##
===========================================
- Coverage    54.42%   54.41%   -0.02%     
===========================================
  Files          632      632              
  Lines        99451    99470      +19     
===========================================
  Hits         54129    54129              
- Misses       45322    45341      +19     

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

[ZHUI]

额，这力直接 import了，后面才判断 is_paddlenlp_ops_available ? 已经晚了吧

[zhink]

done