Fix adaptive p sampler bug with string ban#1287
Merged
ikawrakow merged 9 commits intoikawrakow:mainfrom Feb 20, 2026
Merged
Conversation
Owner
|
As far as I can tell, this rewinds just the last sampled token? Aren't string bans supposed to remove whole sequences of tokens? |
Contributor
Author
You are right. It should handle multi-token rewinds correctly now. |
ikawrakow
approved these changes
Feb 20, 2026
4 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR updates the adaptive p sampler internal state only when selected tokens are not rewinded by string bans.