Repository navigation
ml: plane runtime + neural parity goldens - #797
Merged
Merged
Conversation
PlaneModel (K-pass mask-predict, per-char majority vote, byte-exact render, sha-verified zip contract) ported from the Python reference; cycling tiny-graph fixture (generated once via the py toolchain); env-gated golden e2e with the quantized-tolerance contract - int8 argmax tie-flips across onnxruntime builds are numeric, not logic (3/50 rows, 1-2 char diffs over 600-1000-char rows measured).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes the plane-runtime gap found building the parity corpus (plane existed only in Python). Golden runner uses the quantized tolerance contract with the measured int8 cross-ORT divergence documented.