Fix Inverse kernel rank underflow before indexing trailing dims#28400
Merged
Conversation
Copilot created this pull request from a session on behalf of
tianleiwu
May 7, 2026 17:56
View session
… tests Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/419de619-3846-4724-a919-0bf4bee785a8 Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
tianleiwu
force-pushed
the
copilot/fix-inverse-rank-guard
branch
from
66377d5 to
6b3bcff
Compare
tianleiwu
approved these changes
May 7, 2026
apsonawane
approved these changes
May 15, 2026
This was referenced Jun 20, 2026
deps(nuget): Bump the microsoft-packages group with 1 update
Ellerbach/azure-ai-search-simulator#171
Merged
This was referenced Jun 29, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Inverse::Compute(CPU and CUDA) readdims[num_dim - 2]anddims[num_dim - 1]before validatingnum_dim >= 2. Becausenum_dimissize_t, scalar or 1D inputs silently underflow the subtraction and produce out-of-bounds indices.contrib_ops/cpu/inverse.cc— addORT_RETURN_IF_NOT(num_dim >= 2, ...)immediately after shape retrieval, before any dimension indexing.contrib_ops/cuda/inverse.cc— same guard inComputeInternal.test/contrib_ops/inverse_test.cc— addscalar_input_failsandone_dim_input_failstest cases.Motivation and Context
Without the guard, passing a 0-D or 1-D tensor to the Inverse op causes
size_tunderflow onnum_dim - 2, reading garbage memory before any validation occurs. The fix is a defense-in-depth kernel-level check that mirrors the existing ONNX shape-inference rejection.