fix: apply min-p filtering on softmax probabilities - #1010
Open
Chessing234 wants to merge 1 commit into
Open
Conversation
Compare tokens to min_p * max_prob after softmax (and temperature), matching Hugging Face MinPLogitsWarper instead of raw logits / vocab[0].
Chessing234
force-pushed
the
fix/min-p-sampling-probs
branch
from
August 5, 2026 10:23
692dc2d to
db448f6
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
logits[..., 0]as max probability, which is incorrect.min_p * max_prob, matching Hugging FaceMinPLogitsWarper.efficienly/none top-*).Test plan
sample(..., top_k=0, min_p=0.1)masks low-probability tokens relative to the top softmax massmin_p=0/ greedy (top_k=1) paths unchangedMade with Cursor