Add SA e2e eval framework#222
Merged
Merged
Conversation
timenick
reviewed
Apr 2, 2026
chinazhangchao
previously approved these changes
Apr 2, 2026
timenick
previously approved these changes
Apr 2, 2026
…ft/ModelKit into qiowu/update_sa_e2e_test
DingmaomaoBJTU
dismissed stale reviews from timenick and chinazhangchao
via
2cbbabe
timenick
approved these changes
Apr 2, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
scripts/e2e_eval/run_sa_eval.py: a 4+1 stage self-contained pipeline that exports an HF model, runs SA pre-check, applies capability-driven optimization, runs SA post-check, and optionally compiles to QNN EPContext and diffs predictions against ground truthscripts/e2e_eval/sa_comparison.py: SA Python API invocation, pre/post delta computation, and EPContext diff logicscripts/e2e_eval/sa_report.py: generates an interactive HTML report with per-model SA level breakdowns, optimizer effectiveness stats, and EPContext accuracy.gitignoreto exclude/docs/and/sa_eval_results/output directories🤖 Generated with Claude Code