-
Notifications
You must be signed in to change notification settings - Fork 190
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
Add CB naive chat #644
Add CB naive chat #644
Conversation
That allows LLMPipeline to create ContinuousBatchingPipeline as a backend. There's also a constructor accepting ireq, which can be used if the model was already transformed appropriately for ContinuousBatchingPipeline. But it feels it's going to be misleading and it simpler just to throw if such constructor is called with ContinuousBatchingPipeline backend.
…LMPipeline' into use-CB-as-backend
…-similar-to-LLMPipeline
…LMPipeline' into use-CB-as-backend
build_jenkins |
if (streamer_ptr) { | ||
streamer_ptr->end(); |
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.
Why do we continue to execute this function when streamer is used? Output has already been read and pushed to streamer in above while loop.
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.
That's just API. We document that end() is called in the end. One possible use case to let the streamer to flush the output.
f9e45e1
No description provided.