PaddlePaddle / PaddlePaddle/FastDeploy
多线程通过fd.Runtime()创建多runtime是否会相互影响？
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
- 【系统平台】: Windows x64(Windows10)
- 【硬件】： Nvidia GPU P40， CUDA 11.2 CUDNN 8.2
- 【编译语言】：Python(3.7或3.8等）
问题日志及出现问题的操作流程
我使用多线程创建多个runtime，使用flask作为服务端，在极高的并发下，infer会出现相同的输入，有着不同的结果输出？请问多线程多个runtime同时infer是否会有影响
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
The report mentions Python, Flask, Windows 10, and multiple runtimes created through fd.Runtime() under high concurrency. Start by reproducing concurrent inference with the described setup and compare outputs for identical inputs; done requires determining whether runtimes interfere and documenting a reproducible result or confirmed fix.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- flask, python
- Domain
- ai, api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100