fix: InteractiveExecutor not generating tokens due to early loop exit #1314
Conversation
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
The PostProcess method in InteractiveExecutor was always returning true for breakGeneration, causing the inference loop to exit immediately after the first iteration before any tokens could be generated. Changed the final return statement to return false, allowing generation to continue until a proper stop condition is met (anti-prompt, EOS token, or max tokens reached).
Collaborator
|
Thanks for chasing down this issue. I think the same change is in PR #1261 . I’d prefer to merge the mtmd PR. |
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Outdated suggestions cannot be applied.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.
Fix: InteractiveExecutor not generating tokens
Description
This PR fixes a bug where InteractiveExecutor loads the model successfully but does not generate any response tokens when using
ChatSession.ChatAsync()orExecutor.InferAsync().Issue
The PostProcess method was returning
trueforbreakGenerationin the default fallthrough case, causing the inference loop to exit immediately before any tokens could be sampled.Changes
truetofalse