-
Notifications
You must be signed in to change notification settings - Fork 142
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add RMSNorm (part of parallel_attn_blocks) #448
base: main
Are you sure you want to change the base?
Conversation
Codecov ReportPatch coverage:
Additional details and impacted files@@ Coverage Diff @@
## main #448 +/- ##
==========================================
+ Coverage 69.11% 69.17% +0.06%
==========================================
Files 170 170
Lines 11524 11547 +23
==========================================
+ Hits 7965 7988 +23
Misses 3559 3559
☔ View full report in Codecov by Sentry. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LG! I would just absorb the fp32 type check test into the other one for brevity.
@rohan-varma has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary:
This PR adds RMSNorm.
It is used in parallel_attention_blocks but moving the earlier mono PR for that into smaller chunks for easier review and landing.
Test plan:
added two units tests:
test_rms_norm_fp32
test_rms_core_algo (compares F.norm version vs PR version)
Fixes:
Adds requested doc string to RMSNorm from earlier PR review.