Skip to content

Conversation

@BingooYang
Copy link

📌 Description

修复import flashinfer阶段load cudart.so版本问题,新增从当前程序查询加载的cudart.so路径逻辑,如果路径存在,则加载从程序中查询到的cudart.so版本路径,防止同一个程序中加载不同的cudart.so版本出现显存问题。

🔍 Related Issues

修复FD中import flashinfer导致的内存问题:
https://github.com/PaddlePaddle/FastDeploy/pull/6003/files#

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

  • I have installed pre-commit by running pip install pre-commit (or used your preferred method).
  • I have installed the hooks with pre-commit install.
  • I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

  • Tests have been added or updated as needed.
  • All tests are passing (unittest, etc.).

Reviewer Notes

Copy link

@zoooo0820 zoooo0820 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@BingooYang
Copy link
Author

/re-run all-failed

@BingooYang
Copy link
Author

rebase

@BingooYang BingooYang changed the title fix load cudart.so issues fix loading cudart.so issues Jan 23, 2026
@BingooYang BingooYang merged commit dedaff1 into PFCCLab:paddle Jan 23, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants