Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

docker内存不释放 #1770

Closed
charmowen opened this issue May 6, 2022 · 5 comments
Closed

docker内存不释放 #1770

charmowen opened this issue May 6, 2022 · 5 comments
Assignees
Labels
question Further information is requested

Comments

@charmowen
Copy link

image
客户端请求后,服务端内存不释放,多次请求后内存一直累加。
Paddle Server版本:0.8.3
代码:https://github.com/PaddlePaddle/PaddleClas/tree/release/2.3/deploy/paddleserving

@github-actions
Copy link

github-actions bot commented May 6, 2022

Message that will be displayed on users' first issue

@TeslaZhao
Copy link
Collaborator

和paddle内存使用策略相关,推理默认是 auto_growth
https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/flags/memory_cn.html#flags-allocator-strategy

@TeslaZhao TeslaZhao self-assigned this May 13, 2022
@TeslaZhao TeslaZhao added the question Further information is requested label May 13, 2022
@charmowen
Copy link
Author

单个分类模型,并发数concurrency设置为大于1的数,客户端每次请求内存都不会释放,设置FLAGS_allocator_strategy=naive_best_fit,客户端请求后一直卡住无返回值。该如何设置能够让单模型实现并发且内存及时释放呢?

@Juruobudong
Copy link

单个分类模型,并发数concurrency设置为大于1的数,客户端每次请求内存都不会释放,设置FLAGS_allocator_strategy=naive_best_fit,客户端请求后一直卡住无返回值。该如何设置能够让单模型实现并发且内存及时释放呢?

只是我的问题是显存的

@wangpy1204
Copy link

这个问题解决了吗?遇到同样的问题

@paddle-bot paddle-bot bot closed this as completed Nov 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

4 participants