[serve] Deprecate system-level batching with warning, update the docs #14648
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
architkulkarni
requested changes
Mar 12, 2021
doc/source/serve/tutorials/batch.rst
Outdated
| seconds to wait for a full batch to arrive. The default wait is ``0s`` to | ||
| minimize query latency. You can increase the timeout to improve throughput | ||
| and increase utilization at the cost of some additional latency. | ||
| By default, Ray Serve performs *opportunistic batching*. This means that as |
There was a problem hiding this comment.
This note was the most useful piece of the documentation for me when I was first reading it (though maybe it's very standard and not that useful to others). Is there a way to make it more prominent/move it higher up without disrupting the flow?
There was a problem hiding this comment.
I think it might be fine to just put it all the way at the top after the top-level description of how to do batching. Thoughts?
There was a problem hiding this comment.
I moved it just after the initial code sample, I think that's an improvement. Any earlier is probably confusing. LMK what you think.
Co-authored-by: architkulkarni <architkulkarni@users.noreply.github.com>
Co-authored-by: architkulkarni <architkulkarni@users.noreply.github.com>
Co-authored-by: architkulkarni <architkulkarni@users.noreply.github.com>
Co-authored-by: architkulkarni <architkulkarni@users.noreply.github.com>
|
Thanks for the review @architkulkarni. Addressed the comments, please have another look. |
architkulkarni
approved these changes
Mar 12, 2021
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
Deprecates the existing system-level batching codepath and instead recommends
@serve.batch. The old codepath will still work after this PR, but print a warning pointing at the docs for the new workflow.Related issue number
Checks
scripts/format.shto lint the changes in this PR.