Fix lite-subgraph xpu inference error

[chalsliu]

PR types

Others

PR changes

Others

Description

Fix xpu inference check option error

card-72030

[paddle-bot]

你的PR提交成功，感谢你对开源项目的贡献!
请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

[chalsliu]

修复lite子图xpu推理错误：

[03:08:55][Step 4/6] --------------------------------------
[03:08:55][Step 4/6] C++ Traceback (most recent call last):
[03:08:55][Step 4/6] --------------------------------------
[03:08:55][Step 4/6] 0   paddle::AnalysisConfig::EnableXpu(int, bool, bool, std::string const&, std::string const&, bool, bool)
[03:08:55][Step 4/6] 1   phi::enforce::EnforceNotMet::EnforceNotMet(phi::ErrorSummary const&, char const*, int)
[03:08:55][Step 4/6] 2   phi::enforce::GetCurrentTraceBackString(bool)
[03:08:55][Step 4/6] 
[03:08:55][Step 4/6] ----------------------
[03:08:55][Step 4/6] Error Message Summary:
[03:08:55][Step 4/6] ----------------------
[03:08:55][Step 4/6] PreconditionNotMetError: To use XPU inference, please compile with option 'WITH_XPU' first. (at /home/disk1/teamcity/work/35d35f7d19925f81/Paddle/paddle/fluid/inference/api/analysis_config.cc:201)
[03:08:55][Step 4/6] 

#54342

[zhupengyang]

LGTM

[paddle-bot]

你的PR已合入Paddle库，请关注后续测试结果。
Your PR has been merged into the repository. An official integration test will be conducted later. Stay tuned.