-
Notifications
You must be signed in to change notification settings - Fork 14
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
[Core] Optimize request output tokens putting back implementation to reduce overhead #45
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
s5u13b
commented
Oct 8, 2024
•
edited
Loading
edited
- Previously, we create a seperate thread with asynchrounous event loop to put request output tokens back through zeromq. But we found that it could result in serious performance interference with instance's step under high request load. So we fallback to use a seperate async actor to put request output tokens instead.
- We found that non-blocking ray remote call has ms-level overhead lying in the critical path of llumlet step. So we start a seperate thread to do the remote call to overlap the remote call overhead with llumlet step.
- We view multiple request output tokens as one item of asyncio queue in zeromq server to reduce the awaiting request output tokens overhead of api server.
s5u13b
changed the title
[Misc] Use async actor to put request output tokens back through zeromq
[Core] Use async actor to put request output tokens back through zeromq
Oct 8, 2024
s5u13b
changed the title
[Core] Use async actor to put request output tokens back through zeromq
[Core] Refine request output tokens putting back implementation to reduce overhead
Oct 9, 2024
KuilongCui
reviewed
Oct 9, 2024
KuilongCui
approved these changes
Oct 9, 2024
zhypku
reviewed
Oct 10, 2024
s5u13b
changed the title
[Core] Refine request output tokens putting back implementation to reduce overhead
[Core] Optimize request output tokens putting back implementation to reduce overhead
Oct 10, 2024
zhypku
approved these changes
Oct 10, 2024
KuilongCui
approved these changes
Oct 10, 2024
|
|
|
|
|
|
|
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.