Update base for Update on "[ET-VK] Enable int8 tiled compute shader to be used with buffer tensors"

## Context

As title. Allow the optimized int8 tiled compute shader to be usable for buffer-backed tensors as well.

## Changes

* Generate buffer variants for the int8 linear tiled shader
* Force the scales tensor to always be a buffer to reduce the number of shader variants that need to be generated.
* Generate an additional variant that computes only 1 output row
* Do not require output rows to be an exact multiple of 4 or 6 to use the tiled implementation

Differential Revision: [D73276277](https://our.internmc.facebook.com/intern/diff/D73276277/)

[ghstack-poisoned]

Author: SS-JIA