onnxruntime
onnxruntime copied to clipboard
[WIP] ORT aborts on ConcatFromSequence with empty sequence inputs
- [x] Analyzed the issue: ConcatFromSequence aborts when mixing empty and non-empty tensors with different ranks
- [x] Identified the root cause: validation loop in PrepareForCompute() only checks tensors after the reference tensor, missing validation for tensors before the reference
- [ ] Create test case to reproduce the specific issue (mixing empty and non-empty tensors with different ranks)
- [ ] Fix the validation logic to check ALL tensors against the reference tensor
- [ ] Verify the fix works and doesn't break existing functionality
- [ ] Run existing tests to ensure no regressions
Root cause: In concat.cc PrepareForCompute(), when finding the first non-empty tensor as reference, the validation loop starts from reference_tensor_index + 1, which skips validating empty tensors that appear before the reference tensor. This allows incompatible tensor ranks to pass validation, causing aborts later during computation.
Fixes #16619.
💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.