You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ONNX opset 21 added support for int4 and uint4 of reshape op. So I suppose default CPU EP should support int4 and uint4 data type for reshape op.
Describe scenario use case
For WebNN use case, we need to insert reshape before scale and zeroPoint for dequantizeLinear implementation since ONNX constrains scale and zeroPoint(if exits) must be 1D tensor for per-axis dequantizeLinear. In some scenarios, the data type of zero_point is int4 or uint4.
The text was updated successfully, but these errors were encountered:
Describe the feature request
ONNX opset 21 added support for int4 and uint4 of reshape op. So I suppose default CPU EP should support int4 and uint4 data type for reshape op.
Describe scenario use case
For WebNN use case, we need to insert
reshape
before scale and zeroPoint for dequantizeLinear implementation since ONNX constrains scale and zeroPoint(if exits) must be 1D tensor for per-axis dequantizeLinear. In some scenarios, the data type of zero_point is int4 or uint4.The text was updated successfully, but these errors were encountered: