Fix libaoti_cuda_shims.so not found when importing _portable_lib on Linux

[larryliu0820]

When ExecuTorch is built with CUDA support and installed as a pip package, importing _portable_lib fails with:
ImportError: libaoti_cuda_shims.so: cannot open shared object file

This happens because:

1. _portable_lib.so links against libaoti_cuda_shims.so (via aoti_cuda_backend), but the RPATH only contains a stale build-time temp directory path that no longer exists after installation.
2. setup.py only installs the Windows .lib import library, not the Linux .so shared library.

Fix both issues:

• Add $ORIGIN/../../backends/cuda to the _portable_lib RPATH when CUDA is enabled, following the same pattern used for QNN.
• Add a BuiltFile entry in setup.py to install libaoti_cuda_shims.so into executorch/backends/cuda/ in the pip package.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17632

• 📄 Preview Python docs built from this PR

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

❌ 6 New Failures, 13 Pending, 1 Unrelated Failure

As of commit 99d75e1 with merge base f5e8123 ():

NEW FAILURES - The following jobs have failed:

• pull / android / run-emulator (gh)
  The process '/opt/android/sdk/platform-tools/adb' failed with exit code 224
• pull / test-mediatek-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t e7719faf6df145ba1327b6263a34c8fccbddef15a09e416a924c69b4b76d73cb /exec failed with exit code 2
• pull / test-openvino-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 39dd0d99003300c5b7cb03d3935fc9806e9391129f7888bd7d4d042aa62bbee0 /exec failed with exit code 1
• pull / unittest-buck / linux / linux-job (gh)
  RuntimeError: Command docker exec -t de5acc68d604a3249428236f22481e9d85fb531014e33b398a006dea0d031da1 /exec failed with exit code 3
• Test CUDA Builds / check-all-cuda-builds (gh)
  Process completed with exit code 1.
• Test CUDA Builds / test-executorch-cuda-build-12.6 / linux-job (gh)
  RuntimeError: Command docker exec -t 6bdb0d628d41130f5cb0761a75202d2b74a854bfdf5c5978b4e5b3617d685092 /exec failed with exit code 1

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest-buck / macos / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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

[Gasoonjia]

when would the issue happen? Not seen any failed cuda related ci?

[larryliu0820]

when would the issue happen? Not seen any failed cuda related ci?

When I install nightly. I think when you install from source, it looks inside your pip-out/ directory for the library, which happens to work.