llama-batch: enable parallel sequences for partial rollback#25278
Merged
Conversation
pwilkin
approved these changes
Jul 4, 2026
ggerganov
approved these changes
Jul 8, 2026
ggerganov
left a comment
ggerganov
left a comment
Member
There was a problem hiding this comment.
We should add unit tests for llama_batch_allocr to exercise various splits in a follow-up PR.
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Enable parallel decoding for recurrent models using partial rollback. This is done ensuring that the last
n_keep_tailtokens always belong to the same ubatch insplit_equal.Additional information
Requirements