[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

RMSNorm joins linear in the op samples, with a case module like linear's. The backend test suite has no RMSNorm test, so every case is new: LLM hidden norms at decode and prefill, one over a hidden size that is not a power of two, the query and key norms over the head dim of a 4-D [batch, tokens, heads, 128] tensor, norms with and without a weight, rows whose mean square falls below an eps of 1e-8, down to an all-zero row, rows whose squares overflow float16, an outlier channel, a leading batch dim, an odd hidden size, and dynamic token and batch dims. RMSNorm has no nn.Linear, so it fits only the float scheme: one package of 13 cases in 3 dtypes, each method a single aten.rms_norm.

CMake globs the case modules and the CI workflow already covers the directory, so the existing ggml-CPU sample tests, ggml_sample_test_act_quant and ggml_sample_test_no_linear, pick up the new package with no CI change.

Authored with Claude Code.

Differential Revision: D131119347

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/25094

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures

As of commit d3ef9e0 with merge base 925c1bd ():

NEW FAILURES - The following jobs have failed:

• 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.