Ship the XNNPACK delegate as its own library

[shoumikhin]

The XNNPACK delegate runs many models on CPU, but it is compiled into whichever
component links it. The wheel ships two copies today, one inside the Python
bindings extension and another inside the training extension, and a C++
application cannot get the delegate at all without building it from source.

Build the delegate as a shared library and ship it in the wheel, so a process
has one copy and both the Python bindings and a C++ application can link the
same one.

XNNPACK and its microkernels are built as static libraries, so they are bundled
inside this library rather than left for each consumer to supply. The runtime
and the thread pool are resolved from their shared libraries instead of
embedding another copy of either. Because the delegate now carries XNNPACK
itself, the places that used to name those static libraries explicitly no
longer do so when building shared, which would otherwise ship the same code
twice.

Registration still happens through a static initializer, and the delegate is
retained on the link line so that initializer runs even though no symbol from
it is referenced directly.

This is gated on the existing EXECUTORCH_BUILD_SHARED option, so only the
Linux wheel changes; iOS, Android, and embedded builds keep linking the static
library exactly as before.

Test plan:

The wheel smoke test now asserts that exactly one shipped library defines the
XNNPACK delegate, alongside the existing backend-registry, thread-pool, and CPU
kernel assertions. The symbol it checks was confirmed to exist in the shipped
libraries first, and the assertion was confirmed to fail against a wheel built
before this change, where it correctly reports both copies by name.

Built the wheel from a clean checkout and verified against a fresh virtual
environment with a normal dependency-resolving install:

• The wheel ships the delegate as its own versioned library next to the
  runtime, the thread pool, and the CPU kernels.
• nm -DC across every shipped shared object shows exactly one definition of a
  representative delegate symbol, in the new library rather than in the two
  extensions that used to carry it.
• The delegate still appears in the registered backend list at runtime, which
  confirms its static initializer still runs from the shared library.
• .pte execution through the Python bindings is unchanged, with outputs
  matching eager PyTorch.
• The backend-registry, thread-pool, and CPU kernel assertions all still hold
  with the new library loaded.
• With EXECUTORCH_BUILD_SHARED off, the delegate remains a static library and
  no new shared object is produced, so every build that does not opt in is
  unaffected.

[shoumikhin]

Stack from ghstack (oldest at bottom):

• Ship the CUDA delegate as its own library #21531
• -> Ship the XNNPACK delegate as its own library #21526
• Ship the merged CPU kernels as their own library #21524
• Ship the thread pool as its own library so a process has one pool #21522
• Ship a linkable shared runtime and make the Python bindings use it #21514

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21526

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

⏳ No Failures, 266 Pending

As of commit 0fcd4f5 with merge base d632341 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.