GitLab

disable quant_dot test for CPU backend, it requires removing downcast converts in "ref"implementation. Inside the "ref" impelmentation, it downcasting one of the inputs of the GEMM from float to fp8. Which is a lossy conversion and while computing gemm, it upcasts it back to  float.  CPU backend removes converts completely since it is going from "float->fp8->float". due to lossy cast, results are coming out different.

Ref Unique Operator only

Add min and max reduction modes
Implement duplicate index handling
Add corresponding reference, onnx, and verify tests.

Simplify what we parse the ONNX operator ConstantOfShape into a literal for a static shape

Introduce dilations attribute to pooling operators reference implementation.

Converts dynamic reshapes with constant output dimensions to a static reshape instruction
Intended to be used after split_single_dyn_dim pass and after find_static_dimensions_of makes shape calculations doable at compile-time.