[infernce]Fix bug when copying contiguous CPU tensor to non-contiguous GPU tensor

[bukejiyu]

PR Category

Inference

PR Types

Others

Description

pcard-71500
修复从连续 CPU Tensor 拷贝到不连续 GPU Tensor挂掉的问题

import paddle

dst = paddle.zeros([7168, 1024], dtype="bfloat16")
src = paddle.ones([7168, 576], dtype="bfloat16", device='cpu')

dst = dst[..., :576]
dst.copy_(src)

[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.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@b062fff). Learn more about missing BASE report.

Additional details and impacted files

@@             Coverage Diff             @@
##             develop    #76134   +/-   ##
===========================================
  Coverage           ?   100.00%           
===========================================
  Files              ?         1           
  Lines              ?        84           
  Branches           ?         0           
===========================================
  Hits               ?        84           
  Misses             ?         0           
  Partials           ?         0           

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[wanghuancoder]

LGTM