Anemone220 opened a new issue, #20175:
URL: https://github.com/apache/tvm/issues/20175
### Expected behavior
The Relax ONNX frontend should import a valid ONNX Min with symbolic input
shapes.
### Actual behavior
The script constructs a valid ONNX model. `onnx.checker.check_model` and
ONNX Runtime session construction succeed. `from_onnx` fails while converting
`Min`:
```text
Error converting operator Min, with inputs: [x, y]
Traceback (most recent call last):
...
File ".../python/tvm/relax/frontend/onnx/onnx_frontend.py", line 2420, in
compute_broadcast_shape
target.append(max(ai, bi))
...
ValueError: Cannot use and / or / not operator to Expr, hint: use
tvm.tirx.all / tvm.tirx.any, if it is None checking, use node is not None
```
### Environment
* OS: macOS 15.6 (Darwin 24.6.0, arm64)
* Python: 3.12.2
* TVM: c7b458e946bc4266915da582457476bdcd9705ae (tag v0.26.0; package
reports 0.26.dev0)
* ONNX: 1.17.0
* ONNX Runtime: 1.21.1
* Frontend: `tvm.relax.frontend.onnx.from_onnx`
### Steps to reproduce
The following self-contained script constructs the model:
```python
#!/usr/bin/env python3
"""Reproduce the Relax ONNX symbolic-broadcast Min import failure."""
import onnx
import onnxruntime as ort
from onnx import TensorProto, helper
from tvm.relax.frontend.onnx import from_onnx
def main() -> None:
x = helper.make_tensor_value_info("x", TensorProto.FLOAT, ["n", 4])
y = helper.make_tensor_value_info("y", TensorProto.FLOAT, ["n", 4])
out = helper.make_tensor_value_info("out", TensorProto.FLOAT, ["n", 4])
graph = helper.make_graph(
[helper.make_node("Min", ["x", "y"], ["out"])],
"min_symbolic_broadcast",
[x, y],
[out],
)
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("",
18)])
onnx.checker.check_model(model)
ort.InferenceSession(model.SerializeToString(),
providers=["CPUExecutionProvider"])
from_onnx(model, opset=18, keep_params_in_input=True)
if __name__ == "__main__":
main()
```
### Analysis
`compute_broadcast_shape` uses Python `max` and boolean logic on input
dimensions. When a dimension is a symbolic `tirx.Expr`, Python boolean
conversion raises before a Relax graph is produced.
### Triage
* needs-triage
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
