ConvolutedDog b1918c74fd [Fix][Relax]: ONNX Clip NaN bounds and preserve input NaN (ORT parity) (#19535) ...

This PR fixes https://github.com/apache/tvm/issues/19533:
- Sanitize floating tensor min/max: replace NaN with +inf/-inf before
topi max/min so bounds match ONNX "unbounded" semantics where NaN bounds
default to no constraint.
- After clamping, preserve NaNs from the input tensor on floating
dtypes.
- Extend check_correctness with equal_nan for float outputs containing
NaN.
- Add parametrized Clip opset-13 tests for NaN min/max tensor bounds.

2026-05-12 19:06:06 +08:00

..

tvm

[Fix][Relax]: ONNX Clip NaN bounds and preserve input NaN (ORT parity) (#19535)

2026-05-12 19:06:06 +08:00

.gitignore

Generate requirements.txt from Python spec (#7289)

2021-02-04 06:51:12 -08:00