Update base for Update on "[Ez] Enable Vulkan 4-bit weight only quantization in export_llama"

As title.

Differential Revision: [D64406456](https://our.internmc.facebook.com/intern/diff/D64406456/)

[ghstack-poisoned]

Author: SS-JIA

backends/vulkan/_passes/int4_weight_only_quantizer.py

@@ -4,6 +4,10 @@
 import torch
 import torch.nn.functional as F
 
+from executorch.backends.vulkan._passes.custom_ops_defs import (  # noqa
+    linear_weight_int4_op,
+)
+
 from torchao.quantization.GPTQ import _check_linear_int4_k
 from torchao.quantization.unified import Quantizer
 from torchao.quantization.utils import groupwise_affine_quantize_tensor

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

@@ -209,11 +209,7 @@ void add_q_4w_linear_node(
   ubos.append(graph.strides_ubo(mat2));
   ubos.append(graph.strides_ubo(scales_and_zeros));
 
-  auto out_sizes = graph.sizes_of(out);
-  uint32_t N = utils::val_at(-1, out_sizes);
-  uint32_t M = utils::val_at(-2, out_sizes);
-
-  utils::uvec3 global_wg_size = {N, M, 1};
+  utils::uvec3 global_wg_size = graph.logical_limits_of(out);
   utils::uvec3 local_wg_size = graph.create_local_wg_size(global_wg_size);
 
   graph.execute_nodes().emplace_back(new DispatchNode(