Skip to content

Add hf_profiling_blog_pt1 RMSNorm profiling examples - #1019

Merged
tdalmia-aws merged 1 commit into
aws-neuron:mainfrom
jlonge4:add-hf-profiling-blog-pt1
Oct 20, 2026
Merged

tdalmia-aws merged 1 commit into
aws-neuron:mainfrom
jlonge4:add-hf-profiling-blog-pt1

Conversation

@jlonge4

@jlonge4 jlonge4 commented Oct 20, 2026 •

Copy link
Copy Markdown
Contributor

Description

Add three RMSNorm profiling examples for part 1 of the Hugging Face profiling blog:
naive_rmsnorm.py, torch_rmsnorm.py, and compiled_rmsnorm.py. The files go in
examples/hf_profiling_blog_pt1/.

Related Issue

None. This change adds example files only.

Motivation and Context

The Hugging Face profiling blog (part 1) refers to these examples. They show how to
profile a naive, a PyTorch, and a torch.compile RMSNorm on Neuron with
torch.profiler.

Type of Change

  • Documentation update

Testing

Ran locally (no Neuron hardware needed):

None. This change adds example scripts only. It does not change library code.

Ran on Neuron hardware:

Yes

Checklist

  • Added or updated tests for this change
  • I've performed a self-review for my code
  • Ran the tests, or explained under Testing why I could not
  • Updated the corresponding documentation
  • My changes generate no new warnings
  • Said under Description if an AI assistant helped with this change

Add three RMSNorm examples for part 1 of the Hugging Face profiling blog:
naive_rmsnorm.py, torch_rmsnorm.py, and compiled_rmsnorm.py.

An AI assistant (Claude Code) copied these files from the source repository.
@jlonge4
jlonge4 changed the base branch from contribute-2.33 to main October 20, 2026 16:54
@jlonge4
jlonge4 marked this pull request as ready for review October 20, 2026 16:55
@jlonge4
jlonge4 requested a review from a team as a code owner October 20, 2026 16:55
@tdalmia-aws
tdalmia-aws merged commit 50b1417 into aws-neuron:main Oct 20, 2026
13 of 15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants