[digantdesai]

Stack from ghstack (oldest at bottom):

• -> [executorch][native-vulkan] Lower rms_norm without a weight on the Vulkan engine #25097
• [executorch][vulkan] Make the et_vk.rms_norm weight optional #25096
• [executorch][native-vulkan] Run bf16 methods in f32 on the Vulkan engine #25095
• [executorch][native] Record rms_norm op samples #25094

LowerRMSNorm required a constant weight, so aten.rms_norm with a None weight stayed unlowered and the Vulkan engine rejected it as an unsupported op. Now that et_vk.rms_norm takes an optional weight, the pass also lowers a None weight and passes it through, and the engine binds it as an ET-VK None value. A present weight still has to be a constant of the normalized shape and the input dtype.

The pass now also leaves a norm over a zero-width last dim unlowered, with or without a weight, so it fails as an unsupported op instead of dividing by zero when ET-VK computes the kernel's work grid.

Authored with Claude Code.

Differential Revision: D131119350

NOTE FOR REVIEWERS: This PR has internal Meta-specific changes or comments, please review them on Phabricator!

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/25097

• 📄 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

As of commit 8da889e with merge base 925c1bd ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner (gh)
  >>> Lint for backends/native/runtime/vulkan/passes/LowerRMSNorm.cpp:
• pull / unittest / linux / linux-job (gh)
  RuntimeError: Command bash /__w/_temp/exec_script failed with exit code 1
• pull / unittest / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

[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.