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.

Sign up for GitHub

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

Jump to bottom

[WA] Add API to release memory by unload plugin #1600

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
Draft

[WA] Add API to release memory by unload plugin #1600

wants to merge 2 commits into from
+12 −1

Conversation

sammysun0711
Copy link
Collaborator

@sammysun0711 sammysun0711 commented Jan 20, 2025 •
edited
Loading

CVS-160563

@github-actions github-actions bot added category: LLM LLM pipeline (stateful, static) category: GenAI C++ API Changes in GenAI C++ public headers no-match-files labels Jan 20, 2025
@sammysun0711 sammysun0711 changed the title [WA] release memory by unload plugin per user request [WA] Add API to release memory by unload plugin Jan 20, 2025
ilya-lavrenov
ilya-lavrenov reviewed Jan 24, 2025
View reviewed changes
src/cpp/src/llm_pipeline_stateful.cpp
@@ -399,4 +398,8 @@ void StatefulLLMPipeline::finish_chat() {
}
}

StatefulLLMPipeline::~StatefulLLMPipeline(){
compiled_model.release_memory();
Copy link
Contributor

Choose a reason for hiding this comment

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

it will drop global GPU cache and can affect other models / pipeline running in the same App

Copy link
Contributor

Choose a reason for hiding this comment

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

I have PR with similar solution #1627 where release_memory is not called

Plugin will be unloaded physically, once last pipeline is destructed.

@ilya-lavrenov ilya-lavrenov marked this pull request as draft January 24, 2025 10:08
@ilya-lavrenov ilya-lavrenov self-assigned this Jan 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ilya-lavrenov ilya-lavrenov ilya-lavrenov left review comments

@Wovchena Wovchena Awaiting requested review from Wovchena

@eaidova eaidova Awaiting requested review from eaidova

At least 1 approving review is required to merge this pull request.

Assignees

@ilya-lavrenov ilya-lavrenov

Labels
category: GenAI C++ API Changes in GenAI C++ public headers category: LLM LLM pipeline (stateful, static) do_not_merge no-match-files
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sammysun0711 @ilya-lavrenov