| license: mit | |
| # ExecuTorch Integer Overflow PoC | |
| Commented-out overflow checks in `runtime/executor/program_validation.cpp` lines 35-79. | |
| The `validate_tensor()` function has `c10::mul_overflows` checks that are entirely disabled. | |
| See `executorch_numel_overflow_poc.py` for the PoC generator. | |