add minimum data types and rank range for operations #910

BruceDai · 2025-12-10T09:43:21Z

This PR is to fix #896.
@huningxin @fdwr @reillyeon PTAL, thanks!

index.bs

fdwr · 2025-12-12T04:43:57Z

I checked the unchanged Line 8987, it seems correct by using current 8 indents for to match front
of also 8 indents. Any suggestions? Thanks!

@BruceDai : Remerge with main. My PR adds an extra blank line that pacifies the build error (and yes, that line was already correct, and nothing changed there for months, but bikeshed changed).

index.bs

reillyeon

General wording looks good. I have not validated the specific operator limits specified.

index.bs

fdwr

👀 Thanks for the updates Bruce - I'm sure they were tedious :b.

index.bs

fdwr · 2025-12-16T07:33:54Z

index.bs

  <tr>
    <td>{{input}}</td>
    <td>[=/any data type|any=]</td>
+    <td>{{MLOperandDataType/"float32"}}, {{MLOperandDataType/"float16"}}, {{MLOperandDataType/"int32"}}, {{MLOperandDataType/"int8"}}, {{MLOperandDataType/"uint8"}}</td>


gatherElements includes int8/uint8, but its symmetric counterpart scatterElements does not 😳 I don't know which API has this surprising inconsistency, but I'd rather restrict gatherElements's required data types to exclude int8/uint8 than introduce this asymmetry.

I don't know which API has this surprising inconsistency

It's CoreML: https://apple.github.io/coremltools/source/coremltools.converters.mil.mil.ops.defs.html#coremltools.converters.mil.mil.ops.defs.iOS17.scatter_gather.scatter_along_axis

index.bs

huningxin · 2025-12-17T12:56:01Z

index.bs

  <tr>
    <td>{{input}}</td>
    <td>[=/any data type|any=]</td>
+    <td>{{MLOperandDataType/"float32"}}, {{MLOperandDataType/"float16"}}, {{MLOperandDataType/"int32"}}</td>


ORT doesn't support int32

🤔 An ONNX BitCast operator could help with cases of pure data movement (since no actual math happens) like this one when the operator supports a different data type of the same bit size (sizeof(int32) == sizeof(uint32) == sizeof(float32)). For example, we could call BitCast(int32input, type=float32) -> Triangular -> BitCast(input, type=int32). I'll comment on that ONNX PR.

(update) BitCast operator is pending: onnx/onnx#7527

BruceDai · 2025-12-22T06:29:13Z

Thanks @huningxin and @fdwr for review and identifications. 👍
I submitted a new commit to address your comments. Please take another look, thanks!☕

BruceDai changed the title ~~add minimum data types and rank range for operations~~ [wip]add minimum data types and rank range for operations Dec 11, 2025