[fix][lmi][specdec] fix issue with json output formatter not returnin… #2403
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Outdated suggestions cannot be applied.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.
…g output when iterator is behind
Description
The json output formatter is checking whether the next token in the request is the final token to determine when to provide the response. This works for non speculative decoding cases, but with spec dec we can have multiple tokens returned in 1 "step" call.
Due to how things are structured, with spec dec if we ever generate more than 1 token in a step, the token iterator gets out of sync with the actual status of the request generation, and we get "hanging" behavior.