[ExecuTorch][WebGPU] Add clone op (aten.clone.default)

Pull Request resolved: #20463

`aten.clone.default` is a pure flat copy on the buffer-only WebGPU backend, identical to `view_copy`: `clone_impl` reuses the existing `add_flat_copy` helper (`output[i] = input[i]`) and registers a handler under `aten.clone.default`. No new shader, generated WGSL header, or CMake source — it shares the `view_copy` flat-copy compute pipeline. Required for end-to-end Llama 3.2 1B (4-bit, KV cache): the exported model serializes 2 `aten.clone.default` ops into its runtime operator chain (the RoPE-frequency clones reused across all 16 transformer layers), so without a handler the partition graph-breaks at those nodes. Mirrors the Vulkan delegate, which registers the same op and routes a buffer clone to a flat view-copy.
ghstack-source-id: 397534700
@exported-using-ghexport

@diff-train-skip-merge

Differential Revision: [D109477717](https://our.internmc.facebook.com/intern/diff/D109477717/)

Author: JulianCloudNTH

backends/webgpu/runtime/ops/view_copy/ViewCopy.cpp

@@ -53,10 +53,17 @@ void view_copy_impl(WebGPUGraph& graph, const std::vector<int>& args) {
   add_flat_copy(graph, args.at(0), args.at(args.size() - 1));
 }
 
+// clone = flat copy; survives Vulkan RemoveRedundantOpsTransform in Llama 1B.
+void clone_impl(WebGPUGraph& graph, const std::vector<int>& args) {
+  // args: [self, memory_format?, out]; out = last value-id.
+  add_flat_copy(graph, args.at(0), args.at(args.size() - 1));
+}
+
 } // namespace
 
 WEBGPU_REGISTER_OPERATORS {
   WEBGPU_REGISTER_OP(aten.view_copy.default, view_copy_impl);
+  WEBGPU_REGISTER_OP(aten.clone.default, clone_impl);
 }
 
 } // namespace executorch::backends::webgpu