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.

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

Introduce dilations attribute to pooling operators reference implementation.

Since ONNX opset version 14, layout attribute has been introduced to LSTM operator which allows two predefined layouts for input and output shapes.  Add corresponding reference, onnx, and verify tests.

The inaccuracy was caused by ONNX round requires nearest integer rounding for halway (0.5) cases.
std::round rounds away from zero, thus giving wrong results with halfway cases.
Replaced std::round with std::nearbyint which uses the correct rounding by default.