Report NotFound when a CUDA delegate's weights blob is missing

[shoumikhin]

The CUDA backend moves a model's constants into a separate weights blob and binds them while loading the method. When that blob is not supplied, the load path logged a message at Info level and returned Ok, so the model finished initialising with its constant pointers still null. The program then failed much later, inside a generated kernel, as an illegal memory access:

Invalid __global__ read of size 4 bytes
  at triton_poi_fused_mul_0+0x170
  Address 0x40 is out of bounds

That address is a null base plus a field offset, and the reported error was 0x12 (InvalidArgument) from execute(), which points nowhere near the real cause.

The cached load path already returns NotFound for the same condition, so this makes the other path agree.

A missing blob is genuinely harmless when a model has no constants to bind, and that case is common, so the check keys on the constant count rather than on the blob being absent. get_num_constants is an optional symbol; when it is not available the two cases cannot be told apart, so the previous permissive behaviour is kept.

Before, on a model with three buffers whose blob was not supplied:

RESULT execute RAISED RuntimeError: method->execute() failed with error 0x12

After:

RESULT init RAISED RuntimeError: Failed to load method forward, error: 0x:20

0x20 is Error::NotFound.

Test plan

Added backends/cuda/tests/test_missing_weights_blob.py. It lowers a module with three buffers, checks the externalized blob holds real data rather than being an empty placeholder, then loads the program without it and requires the load to fail.

Verified both directions against a build of this branch:

• without the change: 1 failed, AssertionError: RuntimeError not raised, and the log shows initialisation completing (container handle and CUDA stream both created)
• with the change: 1 passed

Built and ran on an aarch64 CUDA machine with GCC 13.3. clang-format reports no changes for the modified file, and ufmt reports the new test already formatted.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22311

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit f94f8ad with merge base c27baa8 ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (matched linux rule in flaky-rules.json)
  The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.

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

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[linux-foundation-easycla]

• ❌ The email address for the commit (f94f8ad) is not linked to the GitHub account, preventing the EasyCLA check. Consult this Help Article and GitHub Help to resolve. (To view the commit's email address, add .patch at the end of this PR page's URL.) For further assistance with EasyCLA, please visit our EasyCLA portal and chat with our support bot.