Consider adding int64/uint64 data type support for some reduce operators #694
Assignees
Labels
Comments
huningxin
added a commit
to huningxin/webnn
that referenced
this issue
May 27, 2024
`reduceL1`, `reduceProduct`, `reduceSum` and `reduceSumSquare` support already 32-bit integers. 64-bit integers should also be supported. Fix webmachinelearning#283, webmachinelearning#694
huningxin
added a commit
to huningxin/webnn
that referenced
this issue
May 27, 2024
`reduceL1`, `reduceProduct`, `reduceSum` and `reduceSumSquare` already support 32-bit integers. 64-bit integers should also be supported. Fix webmachinelearning#283, webmachinelearning#694
|
Discussed on 2024-10-31: int64/uint64 data type support to be consider together with device selection to find the right abstraction. @huningxin perhaps convert PR #695 to a draft meanwhile? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
One safety checker SD model failed since 'reduceSum' which from Safety Checker requires int64 input type. And currently, WebNN spec only supports int32, uint32, float32 and float16 for reduceSum.
I suppose we should add int64 and uint64 data type for ReduceSum, ReduceSumSquare, ReduceProduct and ReduceL1 which is consistent with DirectML reduce operation definition:
https://learn.microsoft.com/en-us/windows/win32/api/directml/ns-directml-dml_reduce_operator_desc#multiply-and-sum and https://learn.microsoft.com/en-us/windows/win32/api/directml/ns-directml-dml_reduce_operator_desc#l1-and-sum_square.
The text was updated successfully, but these errors were encountered: