Ouadie EL FAROUKI

Extend Gemm operator interface to support mixed precision operations, namely by decoupling matrix A and B type `element_in_t` from output matrix C and scalars alpha and beta type `element_out_t`. Following...

[SYCL] Implementing async model loading for non mapped memory

1

This patch implements most of the event APIs for the SYCL backend, fixes the `set_tensor_async` and enables an async IO / H2D memory copies for model loading _(similar to CUDA...

We add support for logical operators with `vectorized_binary` as well as the relevant unit-tests.