Update base for Update on "[ET-VK] Add reshape functions for transformers related operators"

## Changes

* Implement resize functions for several operators used in Transformers models

## Motivation

Be able to support batched prefill for llama models.

Differential Revision: [D75686049](https://our.internmc.facebook.com/intern/diff/D75686049/)

[ghstack-poisoned]

Author: SS-JIA

backends/vulkan/runtime/graph/ops/DispatchNode.cpp

@@ -75,10 +75,6 @@ void DispatchNode::encode(ComputeGraph* graph) {
 }
 
 void DispatchNode::write_push_constant_data() {
-  if (push_constants_.empty()) {
-    return;
-  }
-
   push_constants_offset_ = 0;
   for (const auto& push_constant : push_constants_) {
     push_constants_offset_ += push_constant.write(