Conversation
angeloskath
reviewed
Feb 4, 2026
|
|
||
| # We have no batch and it actually is not a batchable request | ||
| # so serve single sequence at a time. | ||
| elif batch_generator is None and not is_batchable: |
Member
There was a problem hiding this comment.
Out of curiosity why the change here?
Member
Author
There was a problem hiding this comment.
Because before we load the model it defaults to not batchable. So the first time we check _is_batchable it evaluates to false every time (assuming the model wasn't passed to the server but loaded from the request).
That means that for every first request we will use _serve_single and be in sequential mode even when it could have been batched.
angeloskath
approved these changes
Feb 4, 2026
Member
angeloskath
left a comment
angeloskath
left a comment
There was a problem hiding this comment.
Great!
I left a comment on the moving the _serve_single() around, not against it but wondering why since to me it is a bit more understandable as it were.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes a couple things in batch generation:
MambaCachesince it was causing issues trying to merge it in theArraysCache.mergemethod. (Size parameter was interpreted as the left padding).