[Fix][Relax][ONNX] Preserve integer Div truncation during import

[viiccwen]

ONNX integer Div uses truncating division, rounding toward zero. The Relax ONNX frontend already special-cased integer Div to detect zero divisors, but its PrimExpr folding path could still use NumPy floating-point division when one of the inputs was a shape-derived PrimExpr.

That behavior can produce floating-point TIR values for integer shape/index computations. For example, a Shape -> Gather -> Div -> Slice subgraph can produce T.float64(128.666...) as a Slice bound, which Relax rejects because strided_slice expects integer PrimExpr bounds.

This patch handles scalar integer Div inputs that contain a PrimExpr using TIR truncdiv, preserving ONNX semantics while keeping shape computations in TIR instead of routing them through NumPy. Constant tensor Div continues to use the existing generic binary constant-folding path.

The regression tests cover:

• integer constant folding with negative values to distinguish truncation from floor division
• a shape-derived PrimExpr Div used as a Slice bound
• integer zero-divisor error handling

Verification:

• python -m pytest tests/python/relax/test_frontend_onnx.py::test_div_integer_constant_zero_divisor_raises_valueerror tests/python/relax/test_frontend_onnx.py::test_div_integer_constant_folding_truncates_toward_zero tests/python/relax/test_frontend_onnx.py::test_div_integer_primexpr_folding_truncates_toward_zero -q

Fixes #19974

[gemini-code-assist]

Code Review

This pull request adds support for folding integer division operations involving symbolic PrimExpr inputs in the ONNX frontend, truncating toward zero. It introduces helper methods to identify zero divisors and extract scalar expressions, and adds corresponding unit tests. The review feedback points out that shape-derived values in Relax are often wrapped in relax.PrimValue rather than raw tvm.ir.PrimExprs. To avoid bypassing the symbolic division path and causing potential runtime errors, it is recommended to explicitly check for and unwrap relax.PrimValue in both _as_scalar_prim_expr and the has_prim_expr condition.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[viiccwen]

In the current Relax Python API, relax.prim_value does not produce a separate relax.PrimValue wrapper. It returns a TIR PrimExpr directly for both PrimExpr inputs and Python scalar inputs, so tvm.ir.is_prim_expr(...) already covers these values. I verified this locally, and there does not appear to be a relax.PrimValue Python class to unwrap.

Thx Gemini.

[viiccwen]

cc @guan404ming, @tlopex. 🙌