[ET-VK] Enable buffer implementation of `aten.linear` (#6608)

* [ET-VK] Allow clone op to transfer between memory layouts and storage types

Pull Request resolved: https://github.com/pytorch/executorch/pull/6596

## Changes

As title. Extend the functionality of the `aten.clone` operator to allow transitioning the storage type and memory layout between the input to the output tensor.

## Context

This functionality will be used to transition input tensors to the optimal storage type and memory layout before entering the execution of an op. The transition nodes will be added by a memory metadata tagging pass that will be introduced in a subsequent diff.
ghstack-source-id: 251229412
@exported-using-ghexport

Differential Revision: [D65277710](https://our.internmc.facebook.com/intern/diff/D65277710/)

* [ET-VK] Enable buffer implementation of `aten.linear`

Pull Request resolved: https://github.com/pytorch/executorch/pull/6597

## Changes

As title. Extend the existing buffer implementation of `matmul` to support the linear operator as well.
ghstack-source-id: 251229414
@exported-using-ghexport

Differential Revision: [D65277712](https://our.internmc.facebook.com/intern/diff/D65277712/)

---------

Co-authored-by: Stephen Jia <ssjia@meta.com>