Cache graph traversal and routing for inference#281
Merged
Conversation
Precompute DAG traversal, in/out degrees, and per-layer edge routing after graph mutations instead of rebuilding them on every inference. Replace hash-based branch tracking with dense layer-id indexed state and cached input bindings, preserving the existing tensor flow while removing repeated topology scans from the execution path.
allnes
approved these changes
Mar 14, 2026
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #281 +/- ##
=======================================
Coverage ? 84.77%
=======================================
Files ? 59
Lines ? 3645
Branches ? 2188
=======================================
Hits ? 3090
Misses ? 269
Partials ? 286 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Precompute DAG traversal, in/out degrees, and per-layer edge routing after graph mutations instead of rebuilding them on every inference.
Replace hash-based branch tracking with dense layer-id indexed state and cached input bindings, preserving the existing tensor flow while removing repeated topology scans from the execution path.