Prevent _safe_softmax decomposition in traceand rewire replaceSafeSoftmaxWithSoftmax

[ethansfng]

Summary:
Prevent _safe_softmax from being decomposed in trace(). Re-add ReplaceSafeSoftmaxWithSoftmax pass in apply_torch_ops_passes(), before to_edge().

ISS performance (FLLM_v2_wrist on Artemis_HiFi4_UT_v3):

• Before: 421,662,921 cycles (843ms @ 500MHz)
• After: 214,034,116 cycles (428ms @ 500MHz) — 1.97x speedup

Differential Revision: D105367634

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19619

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• Run pull request jobs on OSDC runners in shadow mode

✅ You can merge normally! (15 Unrelated Failures)

As of commit d6295b6 with merge base 7355d7b ():

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-delegate-linux / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-models-linux (dl3) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-models-linux (mv2) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-models-linux (mv3) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-python-imports-linux / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, operators) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• Test QNN Backend / test-qnn / test-backend-linux (qnn, models) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• Test QNN Backend / test-qnn / test-backend-linux (qnn, operators) / linux-job (gh) (similar failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]

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

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

• pull / test-qnn-passes-linux / linux-job (gh) (trunk failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-sqnr-static-llm-qnn-linux (smollm2_135m) / linux-job (gh) (trunk failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh) (trunk failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]
• pull / test-static-llama-qnn-linux (stories_260k_bc) / linux-job (gh) (trunk failure)
  /pytorch/executorch/examples/qualcomm/oss_scripts/llama/qnn_multimodal_runner.cpp:185:7: error: type 'float' cannot be narrowed to 'bool' in initializer list [-Wc++11-narrowing]

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

[meta-codesync]

@ethansfng has exported this pull request. If you are a Meta employee, you can view the originating Diff in D105367634.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.