-
Notifications
You must be signed in to change notification settings - Fork 231
[2025.4.1] Ignore usage statistics (0 tokens) for legacy text generation pipelines #3845
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
base: releases/2025/4
Are you sure you want to change the base?
Conversation
| } | ||
|
|
||
| // Disabling usage in streaming mode in legacy servable due to the issue with token counting. | ||
| // Fake usage in streaming mode in legacy servable due to the issue with token counting. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
TODO or FIXME for this?
We definitely don't want to leave such comment here for a longer period.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixed
src/test/llm/llmnode_test.cpp
Outdated
| ASSERT_TRUE(responses.back().find("\"finish_reason\":\"length\"") != std::string::npos); | ||
| } | ||
| // For non-continuous batching servables usage is not supported | ||
| // For non-continuous batching servables usage is faked, always returns 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I don't know if I would use word fake - maybe fixed would sound better. And I would keep not supported, because that is the actual state of that feature.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixed
| } | ||
|
|
||
| // Disabling usage in streaming mode in legacy servable due to the issue with token counting. | ||
| // Fake usage in streaming mode in legacy servable due to the issue with token counting. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
| // Fake usage in streaming mode in legacy servable due to the issue with token counting. | |
| // Usage in streaming mode in legacy servable is not supported yet hence we report 0 as a missing metric. |
🛠 Summary
Previously there was a fail during last streaming response
Now it streams correctly, but with usage=0 since it is not supported
It enables use of Continue.dev plugin with legacy pipelines