[ET-VK] Minor fix to conv 2d op using wg_size from create_conv2d_global_wg_size to determine local wg size.

Pull Request resolved: #7450

This diff contains changes to the Convolution.cpp file in the Vulkan backend of Executorch. The changes involve updating the code to use the create_conv2d_global_wg_size function to determine the local workgroup size for the convolution operation. This is done to ensure that the correct workgroup size is used for the operation, which can improve performance.

ghstack-source-id: 260053923
@exported-using-ghexport

Differential Revision: [D67676422](https://our.internmc.facebook.com/intern/diff/D67676422/)

Author: trivedivivek

backends/vulkan/runtime/graph/ops/impl/Convolution.cpp

@@ -370,11 +370,13 @@ void add_conv2d_node(
       weight_data,
       clamp_out);
 
+  utils::uvec3 wg_size = create_conv2d_global_wg_size(graph, method, out);
+
   graph.execute_nodes().emplace_back(new DispatchNode(
       graph,
       shader,
-      create_conv2d_global_wg_size(graph, method, out),
-      graph.create_local_wg_size(out),
+      wg_size,
+      graph.create_local_wg_size(wg_size),
       // Inputs and Outputs
       {{out, vkapi::MemoryAccessType::WRITE},
        {{in, arg_weight, arg_bias}, vkapi::MemoryAccessType::READ}},