PaddlePaddle / PaddlePaddle/FastDeploy
c++GPU多线程推理 程序被挂起.--CPU多线程推理正常
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
温馨提示：根据社区不完全统计，按照模板提问，可以加快回复和解决问题的速度
环境
- 【FastDeploy版本】： fastdeploy-win-x64-gpu-1.0.6
- 【编译命令】预编译库
- 【系统平台】: Windows x64(Windows10)
- 【硬件】： Nvidia GPU1660s， CUDA 11.2
- 【编译语言】： C++
问题日志及出现问题的操作流程
- c++ gpu推理，设置线程3 ，当图片只有一张的时候，后台知道看Thread 2 在运行
- 当在图片集多个图片时，程序会卡住 挂起
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No source file, test, or entry point is named. Start by reproducing the hang with the FastDeploy Windows x64 GPU 1.0.6 package, three C++ threads, and multiple images, then inspect the relevant GPU inference and threading path. Done means multi-image GPU inference completes without hanging while CPU multithreaded inference remains unaffected.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- backend, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100