[Fix][Serialization] Add support for NaN value serialization #18115
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Currently, the
JSONAttrSetter::ParseDoublefunction insrc/node/serialization.cccorrectly handles infinity ("inf","-inf") but does not have a case for Not-a-Number ("nan"). This can cause errors when serializing TVM objects that contain NaN float values.This change adds a condition to explicitly check for the string
"nan"and correctly parse it intostd::numeric_limits<double>::quiet_NaN(). This aligns the NaN handling with the existing logic for infinity values, making the serialization more robust.