Pull Request resolved: #20948

Building ExecuTorch (Vulkan backend plus core runtime) for a Windows x86_64 host with the arvr clang toolchain surfaced three genuine portability defects that fail under its strict `-Werror` set and generated-header wiring. These are correct fixes independent of any warning-suppression workaround.

In `runtime/core/portable_type/c10/c10/targets.bzl`, the arvr-mode `select` that supplies the generated `ATen/Config.h` routed every non-Android OS to `ovrsource_aten_Config.h`, an OVR-native-only `oxx_static_library` that produces no output on the Windows host. The result was `fatal error: 'ATen/Config.h' file not found` in every CPU kernel that includes ATen vec headers. This adds an `ovr_config//os:windows` branch pointing at the working `generated_aten_config_header`, mirroring the existing Android fallback.

In `backends/vulkan/runtime/api/containers/Tensor.h`, `size()` and `dim()` returned `const int64_t` by value; the meaningless top-level `const` on a scalar return trips `-Werror,-Wignored-qualifiers`. This header is included throughout the Vulkan backend, so it blocked `vulkan_graph_runtime`. The `const` qualifier is dropped.

In `extension/data_loader/mman.h` and `mman_windows.cpp`, `#define NOMINMAX` was unconditional while the toolchain already predefines it, tripping `-Werror,-Wmacro-redefined` when compiling `mmap_data_loader` (pulled in by `Module`). Both sites are now guarded with `#ifndef NOMINMAX`.
ghstack-source-id: 402995448
@exported-using-ghexport

Differential Revision: [D112012051](https://our.internmc.facebook.com/intern/diff/D112012051/)

… host

Pull Request resolved: #20949

The arvr Windows clang toolchain enables a stricter `-Werror` warning set than the sanctioned ET build platforms, and vendored third-party headers that ExecuTorch does not own trip it. VMA's `vk_mem_alloc.h` hits `-Werror,-Winconsistent-missing-destructor-override`, and PyTorch's `ATen/cpu/vec/vec_base.h` uses `#if __GNUC__ <= 12` without `defined(__GNUC__)`, hitting `-Werror,-Wundef`. Because the offending code is in vendored headers we cannot patch, this disables warnings-as-errors for the affected compiles, scoped to `ovr_config//os:windows` only, so the clang target compiles are relaxed while the MSVC host tools and all non-Windows platforms are untouched.

`backends/vulkan/targets.bzl` adds `-Wno-error` to the Vulkan targets (VMA header). The CPU-kernel build is split across four independent macros/targets, each of which includes the ATen vec headers and so needs the same relaxation: `kernels/portable/op_registration_util.bzl`, `kernels/optimized/op_registration_util.bzl`, the `binary_ops` support library in `kernels/optimized/cpu/targets.bzl`, and the `libblas` support library in `kernels/optimized/lib_defs.bzl`.
ghstack-source-id: 402995445
@exported-using-ghexport

Differential Revision: [D112012049](https://our.internmc.facebook.com/intern/diff/D112012049/)