runner fix to mitigate the numerical issue (#19286)

[billmguo]

Summary:

Fix 1 — Dangling shared_ptr (2 files)

• runner/static_transformer_runner.h:33
• runner/experimental/static_transformer_runner.h:33

Changed module_(std::shared_ptr(module.get())) to module_(std::move(module)). The old code extracted the raw pointer without releasing ownership, so the unique_ptr destructor would free the Module while the shared_ptr member still pointed to it.

Fix 2 — std::accumulate overflow (2 files)

• llama/runner/static_attention_io_manager.h:58
• runner/experimental/static_attention_io_manager.h:59

Changed std::accumulate(..., 0) to std::accumulate(..., size_t(0)). The int initial value caused the entire accumulation to happen in 32-bit signed arithmetic before assigning to size_t.

Fix 3 — Type-safety check in set_input (4 files)

• llama/runner/static_attention_io_manager.h — added include + size check
• runner/experimental/static_attention_io_manager.h — added include + size check
• runner/static_transformer_runner.h — added size check (include inherited)
• runner/experimental/static_transformer_runner.h — added size check (include inherited)

Added ET_CHECK_MSG(sizeof(T) == elementSize(inputMeta->scalar_type()), ...) before constructing the TensorImpl. This catches mismatches between the runner's compiled types (CacheT, MaskT, RopeT) and the model's actual tensor dtypes at load time, rather than silently reinterpreting data.

Reviewed By: viveknayakatmeta

Differential Revision: D103690468

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19286

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 1 Pending, 4 Unrelated Failures

As of commit 2f878b5 with merge base a0d6e9b ():

NEW FAILURES - The following jobs have failed:

• pull / test-lora-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 3875f2412423d0eb213af38c36f948efa78e5186387b3a431a57036785d2273a /exec failed with exit code 1
• pull / test-voxtral-realtime-xnnpack-linux / linux-job (gh)
  RuntimeError: Command docker exec -t d1c9c96df470259d13a94bd5965c0b024061fe509a56e5a6ea6d8f4122bab3ea /exec failed with exit code 1
• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t 7393d698e1b1c904f6aa4101bb63b7a15fadc89b46034f0e0f537ac72adfca78 /exec failed with exit code 1

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

• pull / unittest / linux / linux-job (gh) (similar failure)
  examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer

BROKEN TRUNK - The following jobs failed but was present on the merge base:

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

• pull / unittest / macos / macos-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• pull / unittest-editable / linux / linux-job (gh) (trunk failure)
  examples/models/llama/tests/test_static_attention.py::StaticAttentionTest::test_within_transformer
• pull / unittest-editable / macos / macos-job (gh) (trunk failure)
  ##[error]The operation was canceled.

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

[meta-codesync]

@billmguo has exported this pull request. If you are a Meta employee, you can view the originating Diff in D103690468.

[YIWENX14]

LGTM. Please fix the lint error before commit.

[YIWENX14]

@pytorchbot label "release notes: none"