fix: trim undecoded final token (on a stop-word/token-budget stop)#362
Merged
jhen0409 merged 1 commit intoJul 10, 2026
Merged
Conversation
a-ghorbani
force-pushed
the
fix/completion-trim-undecoded-final-token
branch
from
July 9, 2026 12:26
4188c5f to
afedcda
Compare
jhen0409
approved these changes
Jul 10, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
During generation, nextToken() pushes the last sampled token to embd but only decodes it on the next nextToken() call. When completion stops on a stop word or the token limit, that next call never runs, so the last token is left in embd without ever being decoded into the KV cache.
An EOS/EOG stop is unaffected as it returns before the push, so embd stays in sync.